Opinion Mining and Sentiment Analysis

Ieee account.

  • Change Username/Password
  • Update Address

Purchase Details

  • Payment Options
  • Order History
  • View Purchased Documents

Profile Information

  • Communications Preferences
  • Profession and Education
  • Technical Interests
  • US & Canada: +1 800 678 4333
  • Worldwide: +1 732 981 0060
  • Contact & Support
  • About IEEE Xplore
  • Accessibility
  • Terms of Use
  • Nondiscrimination Policy
  • Privacy & Opting Out of Cookies

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity. © Copyright 2024 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.

  • Survey Paper
  • Open access
  • Published: 04 December 2021

Opinion mining for national security: techniques, domain applications, challenges and research opportunities

  • Noor Afiza Mat Razali   ORCID: orcid.org/0000-0001-5149-3907 1 ,
  • Nur Atiqah Malizan 1 ,
  • Nor Asiakin Hasbullah 1 ,
  • Muslihah Wook 1 ,
  • Norulzahrah Mohd Zainuddin 1 ,
  • Khairul Khalil Ishak 2 ,
  • Suzaimah Ramli 1 &
  • Sazali Sukardi 3  

Journal of Big Data volume  8 , Article number:  150 ( 2021 ) Cite this article

7741 Accesses

8 Citations

1 Altmetric

Metrics details

Opinion mining, or sentiment analysis, is a field in Natural Language Processing (NLP). It extracts people’s thoughts, including assessments, attitudes, and emotions toward individuals, topics, and events. The task is technically challenging but incredibly useful. With the explosive growth of the digital platform in cyberspace, such as blogs and social networks, individuals and organisations are increasingly utilising public opinion for their decision-making. In recent years, significant research concerning mining people’s sentiments based on text in cyberspace using opinion mining has been explored. Researchers have applied numerous opinions mining techniques, including machine learning and lexicon-based approach to analyse and classify people’s sentiments based on a text and discuss the existing gap. Thus, it creates a research opportunity for other researchers to investigate and propose improved methods and new domain applications to fill the gap.

In this paper, a structured literature review has been done by considering 122 articles to examine all relevant research accomplished in the field of opinion mining application and the suggested Kansei approach to solve the challenges that occur in mining sentiments based on text in cyberspace. Five different platforms database were systematically searched between 2015 and 2021: ACM (Association for Computing Machinery), IEEE (Advancing Technology for Humanity), SCIENCE DIRECT, SpringerLink, and SCOPUS.

This study analyses various techniques of opinion mining as well as the Kansei approach that will help to enhance techniques in mining people’s sentiment and emotion in cyberspace. Most of the study addressed methods including machine learning, lexicon-based approach, hybrid approach, and Kansei approach in mining the sentiment and emotion based on text. The possible societal impacts of the current opinion mining technique, including machine learning and the Kansei approach, along with major trends and challenges, are highlighted.

Various applications of opinion mining techniques in mining people’s sentiment and emotion according to the objective of the research, used method, dataset, summarized in this study. This study serves as a theoretical analysis of the opinion mining method complemented by the Kansei approach in classifying people’s sentiments based on text in cyberspace. Kansei approach can measure people’s impressions using artefacts based on senses including sight, feeling and cognition reported precise results for the assessment of human emotion. Therefore, this research suggests that the Kansei approach should be a complementary factor including in the development of a dictionary focusing on emotion in the national security domain. Also, this theoretical analysis will act as a reference to researchers regarding the Kansei approach as one of the techniques to improve hybrid approaches in opinion mining.

Introduction

Nowadays, cyberspace is consistently loaded with several applications and digital media where people with various backgrounds and expertise share their thoughts and opinions on numerous topics/events. Usually, the information shared by people is textual form-based [ 1 ]. Sharing can be made using any digital media application such as online news, blogs, and social media. Therefore, countless blogs, social media platforms, forums, news reports, e-commerce websites, and other online resources allow people to express opinions. Such information can be utilised to understand public and consumer opinions regarding product preferences, political movements, social events, marketing campaigns, company strategies, and monitoring reputations. People are unaware that the opinions they express have a negative impact on national security. A negative opinion can cause chaos and disputes among a community, which creates opposing views for people of other countries, thereby threatening a state’s national security [ 2 ].

To address this issue, communities of researchers and academicians have been rigorously working on sentiment analysis for the last decade and a half. Sentiment analysis (SA) is a computational assessment of the sentiments, opinions and emotions conveyed in texts and aimed at a certain entity [ 3 ]. Sentiment analysis (also called review mining, opinion mining, attitude analysis or appraisal extraction) is the task of detecting, extracting and classifying opinions, sentiments and attitudes concerning different topics, as expressed in textual input [ 4 ].

Opinion mining or sentiment analysis helps in achieving various goals such as observing public mood regarding political movements [ 5 ], customer satisfaction measurement [ 6 ], movie sales prediction [ 7 ], etc. However, the existing opinion mining method alone, which includes machine learning and lexicon-based approach, cannot effectively help in analysing and classifying people’s sentiments and emotions in cyberspace according to the national security domain because some opinion mining methods only focus on existing domains such as business and education. This paper suggests that the Kansei approach can be a complementary factor in mining and classifying people’s sentiment in other domains, such as the national security domain, by analysing suitable references for this approach.

The Kansei method can apply conventional techniques, such as consumer surveys and expert interviews, to understand people’s reactions towards a certain entity or event with the use of artefacts [ 8 ]. Kansei Engineering is one of the methods based on the Kansei approach, which has been employed in diverse research for emotional design. Kansei Engineering (KE) is capable of measuring people’s feelings and emotional states. These emotional and sensory outcomes are then translated into perceptual design elements of the product or artefact [ 9 ]. Typically, Kansei Words has proven to be excellent in describing affective needs and mapping relationships between Kansei words and design elements to achieve customers’ emotional satisfaction on product specifications. Nowadays, the Kansei approach can be used in different research areas such as education and information technology since the research method of KE had an influential effect on the relationship between the response of emotions and the attributes of any entity. Researchers are using this method in the information technology domain for analysing design elements for online websites. Therefore, this research explores the possible utilisation of KE in combination with other opinion mining methods to analyse emotions from the text.

This paper is structured as follows: Sect. “ Introduction ” provides a brief introduction on opinion mining and the Kansei approach and their functionality and application in mining people’s sentiments in cyberspace. Section “ Method ’ presents the method/research methodology employed in this paper with some explanation. Then, Sect. “ Result ” stated the result of the reviewed article, and Sect. “ Discussion ” explained and discussed the context of the result in depth. Section “ Discussion ” also discuss the finding by highlighting the functionalities of sentiment analysis/opinion mining and the Kansei approach as the new mechanism for mining people’s sentiment and emotions in the national security domain. Also, it presents the challenges of applying machine learning, the lexicon-based approach and the Kansei method for opinion mining based on text in cyberspace. Section “ Future research directions of opinion mining for national security ” discusses future research utilising the hybrid approach of machine learning, the lexicon-based approach and the Kansei approach for opinion mining in the national security domain. Section “ Limitation ” gives out the limitation of our research. Section “ Conclusion ” summarises the work, as well as the conclusion.

To observe the related literature on opinion mining/sentiment analysis and the Kansei approach in mining sentiments based on text in cyberspace, we conducted a systematic literature review of the relevant literature. The following research questions are our focus area on this paper:

How can opinion mining techniques and the Kansei approach enhance the methods of mining people’s sentiments and emotions in cyberspace?

What are the most relevant sectors that benefit from opinion mining which includes the Kansei approach?

What are the techniques used for opinion mining in various domain applications?

What are the challenges and future scope of research for opinion mining techniques that include the Kansei approach?

To answer the research questions above, we conducted the SLR by following the reference guidelines for performing systematic literature reviews in software engineering published by Kitchenham and Charters in 2007. A search has been conducted on five platforms: the ACM (Association for Computing Machinery), IEEE (Advancing Technology for Humanity), SCIENCE DIRECT, SpringerLink, and SCOPUS. Figure  1 presents the research methodology employed to find related articles.

figure 1

Research methodology

Several keywords were selected to be used in this research, such as: “opinion mining,” “sentiment analysis,” “polarity,” “emotion,” “Kansei,” and “opinion mining.” The Web of Science operators such as ‘OR’ and ‘AND had been used in combination with the selected keyword for searching the particular publication. Based on the search platform, this research runs the searching by the keywords, title, or abstract.

Then, the result from the search was filtered through the inclusion or exclusion criteria. The research must follow the inclusion criteria, such as the publication year of the papers must be between 2015 and 2021, and the publication must write in English. The publication must be the focus on the opinion mining techniques based on text in cyberspace. Variety type of discipline was placed on the paper such as computer science, business, psychology, and medicine. Publication in the type of books, posters, and literature review was disregarded.

As the selection result, an initial set total of 1556 research documents was identified. The identified document was reduced to 1475 documents from the preliminary keyword search on the selected platforms. Then, the duplicated document was removed and gave out remaining a total of 1324 documents. The remaining 1324 documents have been checked and read based on the inclusion or exclusion criteria. After that process, a total of 1428 was excluded. The final of 122 relevant papers was included in this research, which is based on the evaluation on reading the full text of the papers. The subsequent section of the literature review involved the analysis of the remaining 122 articles.

In this paper, we study numerous subjects with 122 papers in total. We outline the descriptive statistics from the reviewed article, such as subject-wise analysis, year-wise analysis, and country-wise analysis. The chart in Fig.  2 shows the subject-wise classification; it reveals that Computer Science and Engineering are the major areas in which related research has been published. Social Sciences, Biomedical Science (Medicine), Health, Psychology, Business, Management, and Accounting and Decision Sciences have also observed an increase in the number of research publications on opinion mining/sentiment analysis and the Kansei approach for mining people’s sentiments in cyberspace.

figure 2

Subject-wise Analysis

Based on the year-wise analysis, the significant research in opinion mining for analysing sentiments in cyberspace began from 2015 onwards. We can observe a substantial growth in the number of publications from 2015 to 2018. In 2020, an exponential increase can be seen with more papers published than in 2018, indicating a growing trend in this research area, as shown in Fig.  3 . If we take a closer look at the research, many studies also concentrate on mining sentiments in cyberspace. It indicates that opinion mining is also being explored at a considerably faster rate across multiple industries, partially due to its growing use in various applications.

figure 3

Year-wise Analysis

Figure  4 illustrates the country-wise analysis; it presents the current trend regarding the location where India has the maximum amount of research published for opinion mining or sentiment analysis. However, United Stated (US) is also going forward and increasingly making contributions to the research. It shows that research on opinion mining has the potential to move further in enhancing the detection of people’s opinions in various domains. Asian nations and European nations such as Malaysia, Vietnam, South Korea, the United Kingdom (UK), and Italy also significantly contribute to this research area.

figure 4

Country-wise analysis

Opinion mining overview

Sentiment analysis, also known as opinion mining, has been used to extract and interpret public sentiments and opinions for over a half-century by research communities, academics, government, and service industries. The role of opinion mining is both technically demanding and extremely realistic [ 10 ].

According to Liu [ 11 ], opinion mining/sentiment analysis is known as the computational study of people’s views, appraisals, attitudes and emotions toward individuals, people, problems, events, subjects, and their attributes. It is also the study of people’s opinions based on the sentiments, attitudes, or emotions expressed in a product [ 12 ].

‘A thought, opinion, or concept based on a feeling about a situation’ is the definition of the term “sentiment” according to the Cambridge dictionary [ 13 ]. Opinion mining involves the process of drawing opinions and categorising them according to their polarity, whether they are positive or negative or other emotions. They can be employed for different levels such as document-level sentiment analysis, sentence-level sentiment analysis, and feature or aspect-level sentiment analysis.

Opinion mining has been a research interest since the early twenty-first century. In 2003, Dave et al. [ 14 ] discussed opinion mining and proposed a model for document polarity classification (either recommended or not recommended) based on feedback analysis towards certain entities. From that research onwards, other researchers became interested in applying opinion mining in their text mining studies. It then became new extensive research in the following years. In 2004, Hu and Liu [ 15 ] had investigated the mining approach to summarise product reviews by identifying opinion sentences in each review and deciding whether each opinion sentence is positive or negative. In 2008, Abbasi et al. conducted research on sentiment analysis techniques and their applications [ 16 , 17 ]. In 2009, Tang et al. [ 18 ] discussed document sentiment classification and opinion extraction and experimented with classifying web review opinions for consumer product analysis. In 2010, Chen and Zimbra [ 19 ] assessed the opinions of various business constituents regarding the company by employing an analysis framework that applied automatic topic and sentiment extraction methods to various online discussions. Based on the review of selected articles, this research found that between 2016 until today, opinion mining-related research is still an interesting subject area for researchers.

Classification in opinion mining

There are various classification techniques that exist for sentiment or opinion mining. In classification, content polarity has been identified as a suitable approach to analyse people’s opinions interpreted in text. Usually, three classes are used for classification: positive, negative and neutral. According to the literature, most researchers have classified their sentiments as positive, negative and neutral. Singh et al. [ 20 ] and Akila et al. [ 21 ] had concluded in their findings that positive, negative and neutral opinions toward their entities are adequate. The classification algorithms used for sentiment analysis depend on the method employed, such as the supervised or unsupervised method.

Techniques in performing opinion mining

To conduct opinion mining, researchers have recently applied various methods in the classification of opinions based on textual data. The supervised and unsupervised methods have been used as the classification algorithms. In the basic process of opinion mining, there are two well-known approaches. The unsupervised lexicon-based approach is one approach in which the process is guided by rules and heuristics derived from linguistic knowledge. Another approach is the supervised machine learning approach, where algorithms retrieve inherent information from existing labelled data in order to classify newer, unlabelled data [ 22 ].

Followed by the research question on “What are the techniques used for opinion mining in various domain applications.” Based on the papers reviewed, all had shown the use of either the machine learning techniques, lexicon-based approach, or a mixture of both methods when executing sentiment analysis. The results reveal that opinion mining or sentiment analysis has been conducted in 64 papers using machine learning techniques, while 23 of the reviewed papers applied the lexicon-based approach and 30 papers presented a hybrid approach by combining both methods. Figure 5 displays a chart that contains the number of review papers according to the type of opinion mining technique. The following chart displays the number of review papers according to the type of opinion mining technique. Other techniques were also discussed in these papers, such as the Kansei approach. Five related papers have employed the Kansei approach for mining people’s opinions and emotions.

figure 5

Opinion mining techniques chart

  • Machine learning

The machine learning method is divided into three approaches: supervised learning, unsupervised learning and semi-supervised learning. Supervised learning uses labelled data that facilitate algorithms to learn and predict the sentiment of the text. Usually, to classify the opinion or sentiment of the text, textual data are not labelled, so the focus is on finding the pattern and gaining insight from that data. Based on the reviewed papers, most researchers had used machine learning techniques to analyse people’s opinions in the business domain. They extract people’s opinions from reviews left on e-commerce platforms. Businesses or products such as skin care, mobile phones, movie reviews, banking and train services have applied machine learning techniques for mining people’s opinions regarding their products and goods. Other than that, machine learning techniques are also used in the health and education domains. For the health domain, the machine learning method has been used to mine people’s opinions on health-related issues such as COVID-19 and medicine reviews. In the education sector, researchers have been more focused on the e-learning environment to analyse student reviews regarding e-learning. Government-related domains, such as politics and the economy, also apply machine learning techniques.

Under supervised learning, machine learning methods include the Naïve Bayes Classifier, Support Vector Machine, Decision Tree and Maximum Entropy. Based on the review articles, most methods employed by the researcher have been Naïve Bayes Classifier and Support Vector Machine. In the transportation domain, Mogaji and Erkan [ 23 ] identified the textual data on Twitter that will fall into which sentiments category (positive, negative, or neutral) according to consumer experiences of United Kingdom (UK) train transportation services by using the Naïve Bayes algorithm. Thus, the limitation highlighted by that research was that the automated process was prone to error. It needs the involvement of humans to watch out for that process and stated that human emotion does not fit into just three categories of positive, negative, or natural sentiment. It was different on Naïve Bayes Classifier implemented by Kaur and Kumar [ 24 ] to analyse public opinions on a crisis based on the social media platform. That research had enhanced the method by adding other features that is unigram, it helps in detecting sentiment that can provide useful information to the government in managing crisis situations, but researcher had to state on doing the approach comparison research by comparing this method with other approaches such as Support Vector Machine (SVM) in finding the appropriate sentiment classifier performance on natural disaster domain.

In 2017, Sabuj et al. [ 25 ] used SVM to mine opinions based on data from the web that resulted in satisfactory results when SVM was applied as a polarity classifier. Based on the accuracy comparison value, they found out that the SVM outperformed the Naïve Bayes. The SVM also was employed by Zhang et al. [ 26 ] to explore the negative sentiment tweets on Twitter. Even though that research contributes to identifying the negative features of the text on Twitter, it was observed that a more detailed classification of emotions such as positive was able to be identified by this sentiment analysis method. Ameur et al. [ 27 ] used the SVM classifier to determine the polarity of the "positive or negative" classification for comments on Facebook.

Researchers also use or combine more than one machine learning technique. Based on the reviewed article, the Naïve Bayes algorithm and Support Vector Machine method was most used together to extract opinions and sentiments from textual data from various datasets and social media. More than one method became the most used method in machine learning since the outcome of predicted data is accurate. According to research by Dhahi and Waleed [ 28 ] that employs Naïve Bayes and SVM as machine learning classifiers to extract sentiment from tweet datasets, they found that Naïve Bayes shows acceptable results. Still, it shows a different result from the research performed in [ 29 ], where SVM performed slightly better than NB by adding other features called as stemmed unigram that made the precision value of the SVM method higher than NB. Even though these are the two methods frequently used in mining opinions, other methods such as the maximum entropy and decision tree also have been employed to determine the positive and negative opinions based on a textual dataset but because of the lack of result accuracy. In 2019, Elhadad et al. [ 30 ] proposed an efficient approach in handling Tweets, in Arabic and English languages, with different processing techniques, such as Decision trees and Naïve Bayes. It was identified that the Decision Tree gets the least value on accuracy, and precision acts as a performance measure on those methods.

The supervised learning technique had limitations because machine learning applies the method of training and testing. As a result, researchers need to conduct the time-consuming training phase to get the result. Moreover, a training dataset and testing dataset are usually prepared by employing existing datasets due to requirements in the machine learning method that needs labelled data to train classifiers. It is necessary for datasets used in the experiment to be labelled with an opinion flag. For example, Twitter and movie review datasets are embedded with positive and negative reviews that resulted in the datasets made available with polarity labels (positive, negative, and neutral). Since the classification of sentiments within sentences usually uses machine learning algorithms, thus the input dataset is desired to be labelled.

Random forest, a semi-supervised learning technique, is another method that researchers have implemented in previous studies. In 2018, Khanvilkar and Vora [ 31 ] proposed the use of the random forest as the classification for sentiments on product reviews. The researchers have stated that the random forest machine learning algorithm will help improve sentiment analysis for product recommendations using multiclass classification. In 2020, Suganya and Vijayarani [ 32 ] used the deep learning method in opinion mining. They found that the time taken of execution of random forest was more than the CNN, one of the deep learning methods. Deep learning is a subfield of machine learning that employs deep neural networks. Recently, deep learning algorithms have been widely used in opinion mining. This section provides an overview of papers that have applied deep learning for opinion mining. Deep learning is one of the methods of semi-supervised learning. Imran et al. [ 33 ] used the deep learning method in the health domain. The deep long short-term memory (LSTM) was employed to detect the polarity and emotion on COVID-19 related tweets. That article successfully observed and detected the correlation between sentiments and emotions of people from within neighbouring countries amidst coronavirus (COVID-19) outbreak from their tweets but had some limitations on understanding the tweet context.

Other researchers have also used deep learning methods (such as CNN and LSTM) for analysing the emotional reactions to events of mass violence as well as to enhance the capability and accuracy of the opinion mining method based on a textual dataset by considered properties of users and events, generalized conclusions using several events [ 34 ]. The researcher observed that the CNN model was an appropriate method with meaningful and representative features for prediction. The deep learning method proved to be capable of classifying opinions into positive, negative, and other emotions. However, these supervised algorithms requiring a large dataset to predict the accurate result make this method time-consuming [ 35 ].

Datasets from social media platforms such as Twitter, Facebook and Tumblr are the textual datasets used by researchers. The text mostly consists of user comments, reviews or related research topic words on businesses, products, or events. Researchers have also used existing datasets in cyberspace websites such as IMDB and Amazon review datasets. Several researchers have also applied other dataset platforms such as text in the news, articles and emails. The following Figs. 6 , 7 and 8 presents the distribution of articles according to application, technique and dataset platforms. The machine learning techniques used in opinion mining from the text are summarized in the Tables 1 , 2 , 3 , 4 , 5 , 6 below.

Table 1 summarizes the Naïve Bayes/Bayesian techniques used in opinion mining based on text.

Table 2 summarizes the Support Vector Machine (SVM) techniques used in opinion mining based on text.

Table 3 summarizes the Random Forest (RF) techniques used in opinion mining based on text.

Table 4 summarizes the Decision Tree (DT) techniques used in opinion mining based on text.

Table 5 summarizes the Deep learning techniques used in opinion mining based on text.

Table 6 summarizes the Deep learning techniques used in opinion mining based on text.

figure 6

Chart on the application of machine learning techniques for Opinion mining

figure 7

Chart of machine learning techniques for Opinion mining

figure 8

Dataset platforms used for opinion mining based on machine learning techniques

  • Lexicon-based approach

Another method for opinion mining or sentiment analysis would be the lexicon-based approach. The lexicon-based approach employs a dictionary that incorporates the polarity of the word inside it. If a word is found in a text, it is compared to a word in the dictionary, and the sentiment score is applied. The lexicon-based approach is used to determine sentiment, which is then computed by the overall polarity included in a text.

The lexicon-based approach can be classified under the unsupervised method. This method involves counting the positive and negative words related to the data. This method must also implement a lexicon, known as dictionaries. The dictionaries can be created manually or automatically from existing dictionaries. The difference between this method from machine learning is that it does not depend on or require any training data since it only employs the dictionary.

Through this research, 23 articles that use the lexicon-based approach for opinion mining or sentiment analysis were reviewed and implemented this approach to conduct emotion analysis to determine the sentiments and opinions of the textual dataset. Based on the reviewed articles, most research utilises the lexicon-based approach to extract opinions on business, products and e-commerce domains. Half of the reviewed articles had used a lexicon-based approach for analysing sentiments and emotion data on products and services such as cameras, mobile phones, laptops, tablets, TVs, video surveillance devices and movie reviews. Several types of research have also focused on education and health domains. Researchers employ this approach to analyse people’s opinions on a certain topic related to government issues such as political issues, election-related matters as well as environmental and energy resources.

For the lexicon-based approach, two techniques have been used by researchers: the dictionary-based approach and the corpus-based approach. The first technique, the dictionary-based approach, is employed to pinpoint the opinion words and their polarities.

Usually, to determine sentiments or opinions of the word, the dictionary-based approach is used where synonyms, antonyms and hierarchies in existing lexicons with sentiment information are found. In the existing lexicon, there are three numerical sentiment scores used: Obj(s), Pos(s) and Neg(s), which signify the Objective, Positive and Negative synset. This method is utilised to tag the polarity value with the sentiment dictionary, also known as the sentiment lexicon. Fernández-Gavilanes et al. [ 35 ] had employed the dictionary-based approach to detect opinions on online text such as tweets and reviews. The researcher stated the advantages of this method that can be applied to subject domains other than the domain it was designed for and fix some generic lexicon issues on not context-based by employing a context-based algorithm that helps create a dictionary/lexicon based on a particular context.

Abd et al. [ 80 ] further aimed to recognise the emotional segmentation of a movie reviewer based on the entertainment domain by using this approach to extract sentiments from a given text and classify them. Lexicon based approach helps them achieve a significant result by identifying the contextual polarity for a large subset of sentiment. It was suggested to apply this dictionary idea with machine learning to enhance the accuracy of the result. Also, the researcher had implemented existing dictionaries such as Wordnet and SentiWordNet.

The most used lexicon for the lexicon-based approach, according to the papers reviewed is SentiWordNet. SentiWordNet is the dictionary mostly employed for opinion mining. SentiWordNet is a lexical resource derived from WordNet which assigns numerical values to each synset, representing the scores of positivity, negativity or objectivities [ 81 ]. Each score has a value between 0 and 1, and the sum of positivity, negativity, or objectivity scores is 1. For example, Khan et al. [ 82 ] used the SentiWordNet to create their sentiment dictionary capable of enhancing the polarity classification in sentiment analysis based on movie review dataset and increasing the capability of SentiWordNet.

Even though SentiWordNet is the most frequently used because of the improvement of its usability in opinion mining. Other lexicons, such as MPQA, Wordnet, Vader, and Pattern lexicon was less selected by researchers because of their lack of capabilities in opinion classification. However, it is still able to be applied by researchers for opinion mining. For instance, Wordnet was used as an association list for the opinion classifier of user comments in online media platforms. It was observed that the dictionary enables the classification of irrelevant comments with a high score of precision value but less accuracy in finding relevant and positive comments [ 83 ]. Recently, Dey et al. [ 84 ] used the Vader lexicon, another type of dictionary, compared with other classification methods such as n-gram based SO-CAL approach and Senti-N-Gram lexicon based on those methods in determining the polarity of opinions in a movie review. The results show, the Vader lexicon got less score on accuracy between those two methods.

Other researchers also used an existing dictionary, called the NRC emotion lexicon, for classifying the opinion or polarity according to emotions. The NRC emotion lexicon is a list of words and their corresponding emotions. Eight emotions (fear, sadness, disgust, anger, trust, surprise, anticipation, and joy) and two sentiments (positive and negative) are included in this NRC emotion lexicon. In 2019, Swain and Seeja [ 85 ] employed this lexicon to develop a web-based application that may predict polarity and emotion based on data from Twitter. That lexicon helps classify people’s opinions such as emotions (joy, sadness, disgust, anticipation, trust, fear, surprise, anger, positive and negative) and helps government analyse peoples’ perception with sentiment analysis. However, the web application was only an experiment on the related Tweet on demonetization in India, not in other domains or issues.

As previously mentioned, the other method in the lexicon-based approach is the corpus-based approach. It works when a new sentiment word is recognised based on its mutual relationship. It exploits co-occurrence patterns of words found in unstructured textual documents. In the corpus-based approach, new sentiment words are recognised based on their relationship with other words. This approach can use an existing dictionary or generate a new lexicon based on the research domain to clarify the opinion or sentiment. Deng et al. [ 86 ] had developed a corpus according to the vital research topic regarding social media to be used to extract people’s opinions. The observation of result use for this approach is helpful in domain-specific sentiment classification that is implemented in existing sentiment lexicons. Still, the effectiveness of that method was dependent on the heuristic limitation, which is the frequently co-occurring words are likely to have similar sentiment orientation. The corpus-based approach can be used to analyse the diversity of online opinions that have a potential impact in commercial, industrial and academic environments. However, the extraction and processing of opinions are complex and difficult tasks.

The lexicon-based approach is dependent on lexical resources, and the overall success of the technique is highly dependent on the quality of the lexical resources. It is based on the polarity of a line of text, which may be determined by the polarity of the words that constitute that text. This approach is not meant to address all aspects of language, particularly slang, irony, and negation, because of the complex nature of natural language. Using sentimental language is insufficient. Some issues do exist, such as the fact that some words have varying meanings depending on the application, that some phrases including emotion words might not express any opinion or emotion. From there, this technique has a low recall and a low accuracy. However, the lexicon-based approach has its own advantages, including the following: it can simply count positive and negative words, it is adaptable to many languages and speeds up analysis, and it is fast in terms of processing because it does not require training for its data. The following table displays a summary of review papers on the lexicon-based approach used in opinion mining.

We found that the most applied dataset platform for the lexicon-based approach is the Twitter dataset. Next would be the movie review dataset. Researchers also frequently use other datasets from websites such as online shopping sites. Facebook platforms and blogs have been somewhat utilised depending on the specific research domain. The following Figs. 9 , 10 and 11 presents the distribution of articles according to their application, technique and dataset platforms. Tables 7 and 8 below show the detail of articles that employ the Dictionary based approach and Corpus-based approach.

figure 9

Chart on application of lexicon-based approach for opinion mining

figure 10

Chart on dictionaries used in lexicon-based approach for opinion mining

figure 11

Chart of dataset platforms used in lexicon-based approach for opinion mining

Hybrid approach

Researchers have implemented the hybrid approach in performing opinion mining. The hybrid approach has been implemented to cover up the incapability’s of machine learning and lexicon-based approach by combining two or more methods to achieve better accuracy in extracting and classifying people’s opinions. Based on the reviewed research papers, most researchers use the hybrid approach for opinion mining of products and businesses such as cameras, hairdryers, aircraft, IKEA products and the stock market. It has been further employed in the education and health sectors. Also, we found that the most used machine learning techniques in the hybrid approach are the Naïve Bayes Classifier and Support Vector Machine. Other methods such as the Fuzzy rule-based system, random forest, and deep learning have also been combined with the lexicon-based approach. The most used lexicon/dictionary in the hybrid approach is SentiWordnet, where 16 papers had implemented this lexicon. Other lexicons such as Wordnet, Pattern lexicon, VADER, and NRC Emotion lexicon were also used in this hybrid approach. Mahajan and Rana [ 103 ] had applied eight emotions from the NRC emotion lexicon to quantify public emotion. Several types of research have also used existing sentiment lexicon packages (such as “sentiment r”) and existing dictionaries (such as English sentiment dictionary and Dutch sentiment dictionary). Also, many articles used their own lexicon and combined it with the machine learning method.

Based on research in the business/tourism domain by Chen et al. [ 104 ], the hybrid approach was implemented to construct a tourism sentiment model to achieve text sentiment classification that accurately understood tourist emotions and benefits management and business operations domain. The first method was using the dictionary-based method, which is one of the lexicon-based approaches, to calculate the sentiment value of a single-sentence text. For the second method, the Naïve Bayes machine learning algorithm was used to construct the classifier. Researchers observe that only using a dictionary method has an unacceptable effect on corpus classification. When the NB classifier is used to classify the corpus, the effect will be fixed and improved. Keyvanpour et al. [ 105 ] had implemented the hybrid approach based on lexicon and machine learning to recognize people’s opinions on social networks. The polarity of opinions toward a target word was determined using a method based on the lexicon approach. The textual features of words, sentences, and opinions were analysed and classified using the deep learning method (Neural-fuzzy network). The result from that method had been compared with other supervised methods and found that this method’s speed is slightly slower than other methods because the meta-heuristic algorithm calculates the cost of each member of the population repeatedly using a cost function until determining optimum values for the parameters.

Different from the research by Hamad et al. [ 106 ] used more than one machine learning technique in their hybrid approach for the research that was based on product reviews in the social network. The flow of the approach is identical with the lexicon-based approach is usually the first phase employed lexicon dictionary to determine the sentiment polarity of the sentence, but the machine learning method is used to find and classify the accurate label of polarity and emotion of sentences was different. This research employs the ZeroR, NB, K-NN and Linear SVM as the machine learning method. This approach was compared with some approaches to measure the performance of K-NN, NB and SVM classifiers. It was observed that the K-NN, NB, SVM, and ZeroR have a reasonable accuracy rate. However, the K-NN has outperformed the NB, SVM, and ZeroR based on the achieved accuracy rates and trained model time. The K-NN has achieved the highest accuracy rates of 96.58% and 99.94% for the iPad and iPhone emotion data sets. Despite the result, the researcher highlights the challenge for this approach, such as control of implicit attributes of products, building a summary of opinions based on attributes of products, and dealing with negation opinion expressions. The following Tables 9 and 10 presents a summary of review papers on the hybrid approach used in opinion mining.

The combination of the lexicon-based approach with machine learning is favourable to mine people’s opinions and emotions based on textual datasets according to specific research domains. Datasets from social media platforms such as Twitter and Facebook were seen as the most popular datasets used by researchers based on the reviewed papers. The IMDB movie review dataset comes next, followed by travel review datasets which have become well-known datasets to apply the hybrid approach. The following Figs. 12 , 13 and 14 presents the distribution chart of articles according to application, technique and dataset platforms. The chart in Fig. 14 shows that NB is the most employed machine learning technique and SentiWordNet is one of the popular lexicon types used by the researcher. NB application in opinion predictions for various domains is due to its simplicity and fast processing time. The simple structure of this method makes it easy to implement and results in a high level of effectiveness. Meanwhile, SentiWordNet easy implementation in searching the opinions contributed to the frequent usage of the dictionary by the researchers. In addition, most of the researchers either use only one or more than one of the machine learning methods. For example, several researchers only employed NB or SVM and used a dictionary-based approach as the lexicon-based and the SentiWordNet and NRC emotion lexicon as the lexicon dictionary. Other than that, researchers combine more than one method of machine learning such as Naïve Bayes, Support Vector Machine, Decision Tree (J48) and the dictionary-based approach as their hybrid approach.

figure 12

Chart of applications that used the hybrid approach for opinion mining

figure 13

Chart of dataset platforms used in the hybrid approach for opinion mining

figure 14

Chart of techniques used in the hybrid approach for opinion mining

  • Kansei approach

Recently, in the opinion mining-related domain, the Kansei approach was a new method implemented by the researcher. The Kansei approach has been used to study emotions toward certain entities based on textual data, such as product reviews. After reviewing papers that utilised the Kansei approach, we found that most research had focused on using emotions as the mechanism for measuring people’s expressions toward certain entities. It makes the Kansei approach one of the possible opinion mining approaches that can help in enhancing and improving techniques to mine people’s opinions. Among the existing Kansei approaches frequently used are Kansei Engineering (Type 1) and Kansei evaluation model techniques.

This research has used the Kansei approach to study visual content and investigate the evoked emotions in extremist YouTube videos among younger viewers [ 133 ].The method help in finding the specific emotion regarding content on the online social platform, but it does not involve finding any score of emotion that can help enhance the accuracy of the emotion classification. Different from this, researchers use the Kansei approach to construct the Kansei evaluation model for analysing product design from product reviews on the web by applying NLP methods based on the business/product domain [ 134 ]. From those methods, it can calculate and recognize the related scores evaluated by subjective experiments. The method is useful for products design that is highly had relation to people feeling. However, this method only focused on finding the product design-based people’s opinions according to reviews on online platforms.

Opinion mining using Kansei has not been fully explored yet, but recently, several articles have used the combination of the Kansei methodology with the text mining technique. Based on business/services domain application, Hsiao et al. [ 135 ] had used Kansei Engineering and text mining to analyse opinions regarding hotel services from people’s comments online review. Kansei Engineering, which is one of the methods in the Kansei approach, also uses emotions as the mechanism for evaluating people’s perceptions toward certain entities to mine people’s opinions based on text datasets. The hybrid approach between Kansei Engineering and text mining was effective in extracting and analysing the relationship between the consumer’s emotion and service characteristics that can help to improve the development of services and product for the hotel domain. However, this method had not involved any degree of values on the extracted emotion, and there had the participation of polarity classification. Recently, we can see the development of new research that integrated the Kansei approach and machine learning in mining people’s opinions. Research by Li et al. [ 136 ] was different because it combined Kansei Engineering and machine learning techniques such as Support Vector Machine (SVM) to analyse reviews of online stores from online shopping web pages and had involvement of degree words polarity classification. It was found that the integrated method helped in solving the opinion mining gap that only focused on the polarity classification of the positivity and negativity of the review texts and effectively assisted designers and manufacturers in recognised customers’ emotions to products design through inputting the review texts to facilitate the process of product design. Research of Hsiao et al. and Li et al. have become relevant foundations for the implication of the Kansei approach on another domain. For instance, the combination of the Kansei approach and machine learning technique for opinion mining in the national security domain is a matter that can be further explored. Table 11 presents the list of reviewed articles regarding the Kansei approach.

Drawbacks of opinion mining

Opinions and emotions from textual datasets, such as sentences from reviews, text in online news and blogs and whatever people post on social media, can be extracted using opinion mining techniques. However, the results extracted from opinion mining are in the form of sentiments or opinions, which are either positive, negative or neutral. Specific emotions of opinions, such as anger, sadness, etc., in the domain of national security, have not been fully explored in the opinion mining realm. Several researchers have been extracting emotions based on text. However, challenges exist when extracting emotions from text since more than one technique is needed, and this can require significant time. It must also involve a certain library that functions to look up the right emotion of the word. Some issues also exist when it comes to finding the best technique and method in classifying and extracting people’s opinions and emotions. Each opinion mining technique has its own difficulties and deficiencies. Opinion mining techniques that use machine learning and the lexicon-based approach do not assign identified emotions to specific domains. It would be helpful to mine people’s opinions within text according to specific domains.

Based on all research discussed in this study, Kansei Engineering has proven to be a potential method for evaluating the emotions of a certain entity. Overall, there is a gap to be addressed: combining Kansei Engineering with the opinion mining hybrid approach (the combination of machine learning techniques and lexicon-based approach) to extract and mine existing emotions and opinions within text in cyberspace according to specific domains, such as national security. Moreover, Kansei Engineering involves several steps to assess emotions towards a specimen. In preparing the assessment, there is a need a human involvement to collect a set of evaluation words suitable for evaluating the specimens in interest, arrange the evaluation word space, and choose suitable evaluation words to be used for the assessment. The collection of words from this approach can be utilised to develop a dictionary that can act as a lexicon in mining people’s opinions. It is similar to the existed lexicon such as the NRC emotion lexicon that had the same method in constructing their dictionary. The creation of the list of a word in the NRC emotion lexicon was based on human involvement in finding the word and evaluating the related emotion.

Challenges for utilising machine learning, lexicon-based and Kansei approach in opinion mining

Researchers have been using opinion mining in business and product development sectors because it can help in mining people’s opinions regarding products. From these results, the product capability can be enhanced. Opinion mining is also used in government and health, and its application is still expanding. However, challenges exist in opinion mining applications such as the need for a dictionary that can be used in a different domain to produce a polarity score for a dataset. For example, Fischer and Steiger [ 72 ] have stated that regarding the health sector, limitations do exist on the use of dictionaries when conducting their research. Their problem was finding a specific dictionary for classifying medical literature. Other than that, when extracting emotions based on text, completing such a task is challenging due to the limitation of domain-specific emotion words. It depends on the existing library for scoring the opinions and emotions of words. Asghar et al. [ 138 ] realised that to extract the emotion based on the sentence, and there is a limitation on the ability to incorporate domain-specific words and automatic scoring of such words without performing a lookup operation in the existing library, such as SWN.

There is also a problem with the method used for mining people’s opinions and emotions. Although the Kansei approach has proven to be a method capable of determining people’s emotions regarding certain entities or artefacts, there have been several challenges that require further enhancements for this technique. Most researchers had adopted manual ways to combat this issue, such as making a questionnaire. Finding the right emotion by using this method requires significant time. For example, it has been stated that traditional SD questionnaires are widely used in the Kansei approach. This method is reliable but cumbersome because some research can take several years to complete, and hundreds of respondents must be involved [ 139 ]. This is challenging because Kansei is still a new approach and has limitations such as the lack of a systematic method for assigning scores to entities for emotion evaluation experiments in research. In 2018, Yamada et al. [ 134 ] implemented a text mining technique to perform Kansei evaluation for a product design. They found that the method is useful, and it is in automatic form. However, they had stated that some problems must be fixed such as the necessity to provide an appropriate score to entities used in the subjective evaluation experiment.

Future research directions of opinion mining for national security

Future works should be based on the theoretical findings of the opinion mining method and the systematic literature review accomplished in this research. In our analysis, the results show that opinion mining had been utilised in several popular domains such as business, stock market and entertainment. In the articles surveyed in this SLR, most of the research has reported successful experiments using various techniques to mine people’s opinions based on text in cyberspace. Domain-specific emotion words are the limitation when extracting emotions based on text because of the high dependency on the existing library to determine opinions and emotions of words. Kansei approach has the potential to address the gap. These findings encouraged us to explore elevated techniques for opinion mining-related work in the domain of national security.

National security overview

The end of World War II raised the term “national security” in American politics and held the attention of many throughout those years. The early development of national security had focused more on the military. Nowadays, the present concept covers a broad range of non-military aspects. To fit and adapt to the trending or current occurrences around the world, the concept of national security will continue to develop. National security is a category in political science [ 140 ]. It is a dynamic situation where the state and the society can be protected from threats of armed aggression, political dictatorship, and economic coercion. Two main concepts can define national security: to ensure the nation’s security and to secure the citizens [ 141 ].

When a country confronts direct and indirect threats, the government must mobilise its national security system [ 142 ]. National security refers to a country’s ability to be free from internally or externally threats to its core values. For example, social threats may include hostility from neighbouring nations, invasion of a terrorist group as well as global economic trends that have an impact on the country’s well-being. In distinct cases, dangers or threats may be considered a natural disaster or an outbreak of viral disease. Threats may affect the harmony and sovereignty of the country. Economic, political and social issues are of high interest and often debated in many nations since the elements of national security can be influenced by these issues. Military and non-military are the basic national security elements. Military security is the ability of a nation to secure the nation or intercept military violence from the outside. The non-military element is related to political security, food security, economic security, human security, energy and natural resources security, environmental security, border security, cybersecurity and health security [ 143 ]. Thus, an association between national security elements with citizens’ emotions must be studied so that efforts to maintain and strengthen these elements can be implemented [ 144 ].

Hybrid approach of machine learning, lexicon-based and Kansei approaches for opinion mining in national security domain

Opinion mining is an emerging field of data mining that can be utilised to extract information, such as people’s opinions and emotions, from a vast volume of reviews and text on social platforms regarding any product or topic. Based on the reviewed articles, several methods have been used for opinion mining, such as the machine learning technique, the lexicon-based approach, the hybrid approach and the Kansei approach.

There are many drawbacks and difficulties that have been stated in various research regarding opinion mining techniques, such as lack of specific emotions in opinion mining research and the efficiency of machine learning techniques and lexicon-based approaches. Therefore, this research suggested to employs the Kansei approach that can be combined with machine learning technique and lexicon-based approach as a hybrid approach. However, the liability of the Kansei approach is the use of emotions and the evaluation process in determining the right and specific result of people’s emotions towards an artefact. Even though this method was not annotated with the polarity score, it can be solved by combining the Kansei approach with the machine learning technique and lexicon-based approach for the dictionary establishment for the national security domain. The machine learning technique and lexicon-based approach will help to calculate the text polarity score and enhance the accuracy of the opinion result. Therefore, this research presents a new domain: using the hybrid approach for opinion mining in national security.

Based on the review of the selected papers in the previous chapter, machine learning, lexicon-based approach and the Kansei approach demonstrated their capability of extracting people’s emotions in opinion mining. However, lack of domain-specific emotion words is the limitation faced when extracting emotions based on text due to high dependency on the existing library for scoring the opinions and emotions of words. The existing libraries that included emotions are NRC Word-Emotion Association Lexicon (known as NRC Emotion lexicon or EmoLex) and NRC Emotion Intensity Lexicon (called as Affect Intensity Lexicon). NRC Word-Emotion Association Lexicon is the emotion lexicon constructed for the English language, and it can classify text into eight categories of emotions and sentiment such as anger, anticipation, disgust, fear, joy, sadness, surprise and trust, positive and negative that different from the NRC Emotion Intensity Lexicon. The lexicon is not able to classify text into positive or negative sentiment because it contains the list of English words and their associations with only eight basic emotions (anger, anticipation, disgust, fear, joy, sadness, surprise, trust).

Thus, the Kansei approach can be utilised to complement this gap for the development of a dictionary that incorporates domain-specific words in a specific domain such as national security in opinion mining. For future research, this study suggests adopting a hybrid approach by combining the machine learning method and the lexicon-based approach with the Kansei approach to mine people’s opinions and emotions for national security. The emotions can be used as the parameter to relate with the national security risk using various scenarios such as anger and fear toward certain bad political issues that can bring unwanted risks such as riot, coup, terrorism, and civil war.

Machine learning and lexicon-based approach can classify and predict people’s opinions, while the Kansei approach can be used as a method to clarify people’s emotions in the national security domain. This hybrid approach will enable researchers, businesses and governments to apply the method to observe sentiments and emotions simultaneously for national security observation purposes. The expected output from this combination would be the evaluation of people’s sentiments and emotions with the inclusion of the score value of polarity according to the national security element.

Benefits of performing opinion mining in national security

Various activities in cyberspace pose a risk to national security, such as cyber rumours, fake news websites and hate speech [ 145 ]. These types of threats in cyberspace can be significant risks to national security [ 146 ]. Individuals involved in such activities can indirectly become conspirators since every cyberspace user has a distinct persona, opinion, religion and emotion. They can willingly or unwillingly believe these false rumours and continue to endorse and share them with others. These types of human emotions and behaviours can affect cyberspace. Thus, emotion is deemed a crucial mechanism to detect threats towards national security. Since cyberspace has an emotionally rich nuance and space where people can express their emotions, sentiments and opinions, the connection between emotion and hate speech in cyberspace is undeniable [ 147 ]. Related research on emotion in the national security field had found that fear and anger affect politics, which is one element of national security [ 148 ]. The relation between emotion and national security elements can be seen in how humans react towards issues related to environmental security. A study did find that ‘hope’ is a reaction that people have towards climate change [ 149 ].

The implementation of opinion mining in the national security domain is crucially beneficial. The reason is that most information in the online system is displayed in textual form. A substantial amount of textual data can be generated since it is usual for an individual or persona in cyberspace to express emotions through words or text [ 150 ]. By utilising opinion mining in detecting threats in cyberspace, the state of national security can be strengthened.

This research intends to incorporate all published literature, such as articles, press articles, and research papers, referring to the implementation and application of opinion mining techniques in cyberspace, including the utilisation of the Kansei approach. It uses a systematic literature search methodology to collect valuable information from a collection of available literature. It reveals current developments of opinion mining and the Kansei approach in mining people’s sentiment, paving the road forward for further research. The scope of this work is restricted to the technique of opinion mining and the Kansei approach in mining people’s sentiments based on text to implement in the national security domain. Since 2003, research in this field has been growing and continues at a steady pace of development.

Opinion mining has been a helpful mechanism in finding people’s sentiments and emotions based on text in cyberspace. Based on our research findings, in most of the reviewed papers in this research, various domains do exist that usually employ opinion mining, such as business/products, transportation, health, government, entertainment, and education. It shows the involvement of opinion mining capabilities in various domains. However, there are several drawbacks from the implication of opinion mining techniques that have been discussed in this research. Thus, this study can help as a reference for future research on finding and determining the suitable method for future new research domains such as national security that was suggested. Although mining people’s opinions and emotions for national security is relatively new research, it should be explored and investigated by researchers to enhance the literature within the national security field. This will further secure and strengthen a state’s national security from unwanted threats. This research suggests that the combination of the machine learning method, lexicon-based approach and the Kansei approach can be a possible mechanism for evaluating people’s emotions within the text. This includes the text’s opinion polarity and possible emotions flag that can influence people’s acceptance of information in cyberspace.

Availability of data and materials

All papers studied in this systematic review are available in SCOPUS, IEEE Xplore, ACM Digital Library, SPRINGERLINK and ScienceDirect. Please see the references below.

Abbreviations

Association for Computing Machinery

Advancing Technology for Humanity

Natural Language Processing

Coronavirus disease 2019

Kansei Engineering

Long short-term memory

Logistic Regression

Naïve Bayes

Support Vector Machines

Decision Tree

Stochastic Gradient Descent

Neural Network

Random Forest

Latent Dirichlet Allocation

K-Nearest Neighbour

Multilabel K-Nearest Neighbours

Maximum Entropy

Conditional Random Fields

Adaptive Boosting

Best-First Decision Tree

Convolutional Neural Network

Artificial Neural Network

Deep Belief Network

Deep Neural Network

Recurrent Neural Network

Gated Recurrent Unit

Bidirectional Encoder Representations from Transformers

Back-Propagation Neural Networks

Semantic differential

Internet Movie Database

Point-wise mutual information

Multi-Perspective Question Answering

SentiWordNet

Valence Aware Dictionary and Sentiment Reasoner

Hannigan TR, et al. Topic modeling in management research: rendering new theory from textual data. Acad Manag Ann. 2019;13(2):586–632. https://doi.org/10.5465/annals.2017.0099 .

Article   Google Scholar  

Stevens D, Vaughan-Williams N. Citizens and security threats: issues, perceptions and consequences beyond the national frame. Br J Polit Sci. 2014;46(1):149–75. https://doi.org/10.1017/S0007123414000143 .

Cambria E. Affective computing and sentiment analysis. IEEE Intell Syst. 2016;31:102–7. https://doi.org/10.1109/MIS.2016.31 .

Zhang L, Liu B. Sentiment analysis and opinion mining. In: Sammut C, Webb GI, editors. Encyclopedia of machine learning and data mining. Boston: Springer US; 2017. p. 1152–61.

Chapter   Google Scholar  

Preoctiuc-Pietro D, Liu Y, Hopkins D, Ungar L. Beyond binary labels: political ideology prediction of Twitter users. 2017. https://doi.org/10.18653/v1/p17-1068 .

Xu F, Pan Z, Xia R. E-commerce product review sentiment classification based on a naïve Bayes continuous learning framework. Inf Process Manag. 2020;57(5): 102221. https://doi.org/10.1016/j.ipm.2020.102221 .

Rachiraju SC, Revanth M. Feature extraction and classification of movie reviews using advanced machine learning models. 2020. https://doi.org/10.1109/iciccs48265.2020.9120919 .

Yang YP, Chen DK, Gu R, Gu YF, Yu SH. Consumers’ Kansei needs clustering method for product emotional design based on numerical design structure matrix and genetic algorithms. Comput Intell Neurosci. 2016;2016:1–11. https://doi.org/10.1155/2016/5083213 .

Nagamachi M. Kansei/affective engineering and history of Kansei/affective engineering in the world. In: Kansei/affective engineering. CRC Press, 2010, pp. 1–12.

Aggarwal CC, Zhai C, editors. Mining text data. Springer US, 2012.

Liu B. Opinion mining and sentiment analysis. In: Web data mining. Springer Berlin Heidelberg, 2011, pp. 459–526.

Isabelle G, Maharani W, Asror I. Analysis on opinion mining using combining lexicon-based method and multinomial Naïve Bayes. vol. 2, No. IcoIESE 2018, pp. 214–219, 2019. https://doi.org/10.2991/icoiese-18.2019.38 .

Cambridge Dictionary, “Sentiment definition.” 2021, [Online]. Available: https://dictionary.cambridge.org/dictionary/english/sentiment .

Dave K, Lawrence S, Pennock D. Mining the peanut gallery: opinion extraction and semantic classification of product reviews. Min Peanut Gall Opin Extr Semant Classif Prod Rev 2003;775152. https://doi.org/10.1145/775152.775226 .

Hu M, Liu B. Mining and Summarizing Customer Reviews. In: Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2004, pp. 168–177. https://doi.org/10.1145/1014052.1014073 .

Abbasi A, Chen H, Salem A. Sentiment analysis in multiple languages: feature selection for opinion classification in Web forums. ACM Trans Inf Syst. 2008;26(3):1–34. https://doi.org/10.1145/1361684.1361685 .

Zhang C, Zuo W, Peng T, He F. Sentiment classification for Chinese reviews using machine learning methods based on string kernel. 2008. https://doi.org/10.1109/iccit.2008.51 .

Tang H, Tan S, Cheng X. A survey on sentiment detection of reviews. Expert Syst Appl. 2009;36(7):10760–73. https://doi.org/10.1016/j.eswa.2009.02.063 .

Chen H, Zimbra D. AI and opinion mining. IEEE Intell Syst. 2010;25(3):74–80. https://doi.org/10.1109/MIS.2010.75 .

Singh N, Sharma N, Juneja A. Sentiment score analysis for opinion mining. In: Advances in intelligent systems and computing. Springer Singapore, 2018, pp. 363–374.

Akila R, Revathi S, Shreedevi G. Opinion mining on food services using topic modeling and machine learning algorithms. 2020. https://doi.org/10.1109/icaccs48705.2020.9074428 .

Pang B, Lee L, Vaithyanathan S. “Thumbs up? Sentiment Classification using Machine Learning Techniques. In: Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing ({EMNLP} 2002), 2002, pp. 79–86. https://doi.org/10.3115/1118693.1118704 .

Mogaji E, Erkan I. Insight into consumer experience on UK train transportation services. Travel Behav Soc. 2019;14:21–33. https://doi.org/10.1016/j.tbs.2018.09.004 .

Kaur HJ, Kumar R. Sentiment analysis from social media in crisis situations. 2015. https://doi.org/10.1109/ccaa.2015.7148383 .

Sabuj MS, Afrin Z, Hasan KMA. Opinion Mining Using Support Vector Machine with Web Based Diverse Data. In: Lecture Notes in Computer Science. Springer International Publishing, 2017, pp. 673–678.

Zhang L, Dong W, Mu X. Analysing the features of negative sentiment tweets. Electron Libr. 2018;36(5):782–99. https://doi.org/10.1108/EL-05-2017-0120 .

Ameur H, Jamoussi S, Ben Hamadou A. Sentiment lexicon enrichment using emotional vector representation. 2017. https://doi.org/10.1109/aiccsa.2017.151 .

Dhahi SH, Waleed J. Emotions polarity of tweets based on semantic similarity and user behavior features. 2020. https://doi.org/10.1109/it-ela50150.2020.9253088 .

Banik N, Rahman MHH. Evaluation of Naïve Bayes and Support Vector Machines on Bangla Textual Movie Reviews. 2018. https://doi.org/10.1109/icbslp.2018.8554497 .

Elhadad MK, Li KF, Gebali F. Sentiment Analysis of Arabic and English Tweets. In: Advances in Intelligent Systems and Computing, Springer International Publishing, 2019, pp. 334–348.

Khanvilkar G, Vora D. Sentiment analysis for product recommendation using random forest. Int J Eng Technol. 2018;7(3):87–9. https://doi.org/10.14419/ijet.v7i3.3.14492 .

Suganya E, Vijayarani S. Sentiment Analysis for Scraping of Product Reviews from Multiple Web Pages Using Machine Learning Algorithms. In: Advances in Intelligent Systems and Computing, Springer International Publishing, 2019, pp. 677–685.

Imran AS, Daudpota SM, Kastrati Z, Batra R. Cross-cultural polarity and emotion detection using sentiment analysis and deep learning on COVID-19 related tweets. IEEE Access. 2020;8(October):181074–90. https://doi.org/10.1109/ACCESS.2020.3027350 .

Harb JGD, Ebeling R, Becker K. A framework to analyze the emotional reactions to mass violent events on Twitter and influential factors. Inf Process Manag. 2020;57(6): 102372. https://doi.org/10.1016/j.ipm.2020.102372 .

Fernández-Gavilanes M, Álvarez-López T, Juncal-Martínez J, Costa-Montenegro E, Javier González-Castaño F. Unsupervised method for sentiment analysis in online texts. Expert Syst Appl. 2016;58:57–75. https://doi.org/10.1016/j.eswa.2016.03.031 .

Kunal S, Saha A, Varma A, Tiwari V. Textual dissection of live Twitter reviews using Naive Bayes. Procedia Comput Sci. 2018;132:307–13. https://doi.org/10.1016/j.procs.2018.05.182 .

Lee J, Benjamin S, Childs M. Unpacking the emotions behind TripAdvisor travel reviews: the case study of Gatlinburg, Tennessee. Int J Hosp Tour Adm. 2020;00(00):1–18. https://doi.org/10.1080/15256480.2020.1746219 .

Sathya V, Venkataramanan A, Tiwari A, DD PS. Ascertaining Public Opinion Through Sentiment Analysis. 2019. https://doi.org/10.1109/iccmc.2019.8819738 .

Anand D, Naorem D. Semi-supervised aspect based sentiment analysis for movies using review filtering. Procedia Comput Sci. 2016;84:86–93. https://doi.org/10.1016/j.procs.2016.04.070 .

Chawla S, Dubey G, Rana A. Product opinion mining using sentiment analysis on smartphone reviews. 2017. https://doi.org/10.1109/icrito.2017.8342455 .

Bhargava MG, Rao DR. Sentimental analysis on social media data using R programming. Int J Eng Technol. 2018;7(2):80–4. https://doi.org/10.14419/ijet.v7i2.31.13402 .

Pugsee P, Nussiri V, Kittirungruang W. Opinion Mining for Skin Care Products on Twitter. In: Communications in Computer and Information Science. Springer Singapore, 2018, pp. 261–271.

Rane PS, Khan RA. Ranked rule based approach for sentiment analysis. 2018. https://doi.org/10.1109/icrieece44171.2018.9008647 .

Al-Saffar A, Awang S, Tao H, Omar N, Al-Saiagh W, Al-bared M. Malay sentiment analysis based on combined classification approaches and Senti-lexicon algorithm. PLoS ONE. 2018;13(4):1–18. https://doi.org/10.1371/journal.pone.0194852 .

Shrestha H, Dhasarathan C, Munisamy S, Jayavel A. Natural language processing based sentimental analysis of Hindi (SAH) script an optimization approach. Int J Speech Technol. 2020;23(4):757–66. https://doi.org/10.1007/s10772-020-09730-x .

Arif F, Dulhare UN. A machine learning based approach for opinion mining on social network data. In: Lecture Notes in Networks and Systems. Springer Singapore, 2017, pp. 135–147.

Tripathy A, Agrawal A, Rath SK. Classification of sentiment reviews using n-gram machine learning approach. Expert Syst Appl. 2016;57:117–26. https://doi.org/10.1016/j.eswa.2016.03.028 .

Elzayady H, Badran KM, Salama GI. Sentiment analysis on Twitter data using Apache Spark Framework. 2018. https://doi.org/10.1109/icces.2018.8639195 .

Singh J, Singh G, Singh R, Singh P. Optimizing accuracy of sentiment analysis using deep learning based classification technique. Commun Comput Inf Sci. 2018;799:516–32. https://doi.org/10.1007/978-981-10-8527-7_43 .

Article   MATH   Google Scholar  

Bansal B, Srivastava S. Sentiment classification of online consumer reviews using word vector representations. Procedia Comput Sci. 2018;132:1147–53. https://doi.org/10.1016/j.procs.2018.05.029 .

Akkarapatty N, Raj N. A machine learning approach for classification of sentence polarity. 2016, pp. 316–321. https://doi.org/10.1109/SPIN.2016.7566711 .

Hiremath BN, Patil MM. Enhancing optimized personalized therapy in clinical decision support system using natural language processing. J King Saud Univ Comput Inf Sci. 2020. https://doi.org/10.1016/j.jksuci.2020.03.006 .

Yueyang L, Wang YZ. Detecting opinion polarities using ensemble of classification algorithms. J Phys Conf Ser. 2019;1229(1):012065. https://doi.org/10.1088/1742-6596/1229/1/012065 .

Poornima A, Priya KS. A comparative sentiment analysis of sentence embedding using machine learning techniques. 2020. https://doi.org/10.1109/icaccs48705.2020.9074312 .

Charoensuk J, Sornil O. A hierarchical emotion classification technique for Thai reviews. J ICT Res Appl. 2018;12(3):280–96. https://doi.org/10.5614/itbj.ict.res.appl.2018.12.3.6 .

Ruseti S, Sirbu MD, Calin MA, Dascalu M, Trausan-Matu S, Militaru G. Comprehensive exploration of game reviews extraction and opinion mining using nlp techniques. Adv Intell Syst Comput. 2020;1041(February):323–31. https://doi.org/10.1007/978-981-15-0637-6_27 .

Barrón Estrada ML, Zatarain Cabada R, Oramas Bustillos R, Graff M. Opinion mining and emotion recognition applied to learning environments. Expert Syst Appl. 2020;150:113265. https://doi.org/10.1016/j.eswa.2020.113265 .

Rathee N, Joshi N, Kaur J. Sentiment analysis using machine learning techniques on Python. 2018. https://doi.org/10.1109/iccons.2018.8663224 .

Jayakrishnan R, Gopal GN, Santhikrishna MS. Multi-class emotion detection and annotation in malayalam novels. 2018. https://doi.org/10.1109/iccci.2018.8441492 .

Babu MY, Vijaya Pal Reddy P, Shoba Bindu C. Aspect category detection using multi label multi class support vector machine with semantic and lexical features. J Adv Res Dyn Contr Syst. 2020;12(1):398–405. https://doi.org/10.5373/JARDCS/V12I1/20201920 .

Gan D, Shen J, Xu M, Stamenkovic Z. Adaptive learning emotion identification method of short texts for online medical knowledge sharing community. Comput Intell Neurosci. 2019;1–10:2019. https://doi.org/10.1155/2019/1604392 .

Varsha K, Monica R. Analyzing of premier institution using twitter data on real-time basis. 2017. https://doi.org/10.1109/icecds.2017.8389968 .

Kumar HMK, Harish BS, Kumar SVA, Aradhya VNM. Classification of sentiments in short-text. 2018. https://doi.org/10.1145/3184066.3184074 .

Krishna BV, Pandey AK, Kumar APS. Feature based opinion mining and sentiment analysis using fuzzy logic. In: Cognitive Science and Artificial Intelligence, Springer Singapore, 2017, pp. 79–89.

Zhan M, Tu R, Yu Q. Understanding Readers. 2018. https://doi.org/10.1145/3297156.3297270 .

M. S. R. Hitesh, V. Vaibhav, Y. J. A. Kalki, S. H. Kamtam, and S. Kumari, “Real-Time Sentiment Analysis of 2019 Election Tweets using Word2vec and Random Forest Model,” Sep. 2019, doi: https://doi.org/10.1109/icct46177.2019.8969049 .

Halim Z, Waqar M, Tahir M. A machine learning-based investigation utilizing the in-text features for the identification of dominant emotion in an email. Knowledge-Based Syst. 2020;208: 106443. https://doi.org/10.1016/j.knosys.2020.106443 .

Mahalakshmi S, Elango S. Cross domain sentiment analysis using different machine learning techniques. 2015, pp. 77–87.

Shrivastava A, Regunathan R, Pant A, Srujan CS. Document-level analysis of sentiments for various emotions using hybrid variant of recursive neural network. Adv Intell Syst Comput. 2019;828:641–9. https://doi.org/10.1007/978-981-13-1610-4_65 .

Zheng, Y. Opinion Mining from news articles. In: Advances in intelligent systems and computing. Springer Singapore, 2018, pp. 447–453.

Saleh SN, Lehmann CU, McDonald SA, Basit MA, Medford RJ. Understanding public perception of coronavirus disease 2019 (COVID-19) social distancing on Twitter. Infect Control Hosp Epidemiol. 2021;42(2):131–8. https://doi.org/10.1017/ice.2020.406 .

Fischer I, Steiger HJ. Toward automatic evaluation of medical abstracts: the current value of sentiment analysis and machine learning for classification of the importance of PubMed abstracts of randomized trials for stroke. J Stroke Cerebrovasc Dis. 2020;29(9): 105042. https://doi.org/10.1016/j.jstrokecerebrovasdis.2020.105042 .

Medford RJ, Saleh SN, Sumarsono A, Perl TM, Lehmann CU. An ‘Infodemic’: leveraging high-volume twitter data to understand early public sentiment for the Coronavirus disease 2019 outbreak. Open Forum Infect. Dis. 2020;7(7). https://doi.org/10.1093/ofid/ofaa258 .

Zhang X, Li W, Ying H, Li F, Tang S, Lu S. Emotion detection in online social networks: a multilabel learning approach. IEEE Internet Things J. 2020;7(9):8133–43. https://doi.org/10.1109/JIOT.2020.3004376 .

Sankar H, Subramaniyaswamy V, Vijayakumar V, Arun Kumar S, Logesh R, Umamakeswari A. Intelligent sentiment analysis approach using edge computing-based deep learning technique. Softw Pract Exp. 2020;50(5):645–57. https://doi.org/10.1002/spe.2687 .

Gopalakrishnan V, Ramaswamy C. Patient opinion mining to analyze drugs satisfaction using supervised learning. J Appl Res Technol. 2017;15(4):311–9. https://doi.org/10.1016/j.jart.2017.02.005 .

Rao G, Huang W, Feng Z, Cong Q. LSTM with sentence representations for document-level sentiment classification. Neurocomputing. 2018;308:49–57. https://doi.org/10.1016/j.neucom.2018.04.045 .

Le NC, Lam NT, Nguyen SH, Nguyen DT. On Vietnamese sentiment analysis: a transfer learning method. 2020. https://doi.org/10.1109/rivf48685.2020.9140757 .

Kalaivani P, Dinesh D. Machine learning approach to analyze classification result for twitter sentiment. 2020. https://doi.org/10.1109/icosec49089.2020.9215278 .

Abd DH, Abbas AR, Sadiq AT. Analyzing sentiment system to specify polarity by lexicon-based. Bull Electr Eng Informatics. 2021;10(1):283–9. https://doi.org/10.11591/eei.v10i1.2471 .

Rao VA, Anuranjana K, Mamidi R. A Sentiwordnet strategy for curriculum learning in sentiment analysis. In: Natural language processing and information systems. 2020, pp. 170–178.

Khan FH, Qamar U, Bashir S. SentiMI: introducing point-wise mutual information with SentiWordNet to improve sentiment polarity detection. Appl Soft Comput J. 2016;39:140–53. https://doi.org/10.1016/j.asoc.2015.11.016 .

Kavitha KM, Shetty A, Abreo B, D’Souza A, Kondana A. Analysis and classification of user comments on YouTube videos. Procedia Comput Sci. 2020;177:593–8. https://doi.org/10.1016/j.procs.2020.10.084 .

Dey A, Jenamani M, Thakkar JJ. Senti-N-Gram: an n-gram lexicon for sentiment analysis. Expert Syst Appl. 2018;103:92–105. https://doi.org/10.1016/j.eswa.2018.03.004 .

Swain S, Seeja KR. TWEESENT: a Web application on sentiment analysis. Adv Intell Syst Comput. 2019;851:393–400. https://doi.org/10.1007/978-981-13-2414-7_36 .

Deng S, Sinha AP, Zhao H. Adapting sentiment lexicons to domain-specific social media texts. Decis Support Syst. 2017;94:65–76. https://doi.org/10.1016/j.dss.2016.11.001 .

Azizan A, Jamal NNSK, Abdullah MN, Mohamad M, Khairudin N. Lexicon-based sentiment analysis for movie review tweets. 2019. https://doi.org/10.1109/aidas47888.2019.8970722 .

Khan FH, Qamar U, Bashir S. eSAP: A decision support framework for enhanced sentiment analysis and polarity classification. Inf Sci (Ny). 2016;367–368:862–73. https://doi.org/10.1016/j.ins.2016.07.028 .

Abdar M, et al. Energy choices in Alaska: mining people’s perception and attitudes from geotagged tweets. Renew Sustain Energy Rev. 2020;124: 109781. https://doi.org/10.1016/j.rser.2020.109781 .

Wook M, et al. Opinion mining technique for developing student feedback analysis system using lexicon-based approach (OMFeedback). Educ Inf Technol. 2020;25(4):2549–60. https://doi.org/10.1007/s10639-019-10073-7 .

Aslam F, Awan TM, Syed JH, Kashif A, Parveen M. Sentiments and emotions evoked by news headlines of coronavirus disease (COVID-19) outbreak. Humanit Soc Sci Commun. 2020;7(1):1–10. https://doi.org/10.1057/s41599-020-0523-3 .

Garcia MB. Sentiment analysis of tweets on coronavirus disease 2019 (COVID-19) pandemic from Metro Manila, Philippines. Cybern Inf Technol. 2020;20(4):141–55. https://doi.org/10.2478/cait-2020-0052 .

Song C, Guo J, Zhuang J. Analyzing passengers’ emotions following flight delays- a 2011–2019 case study on SKYTRAX comments. J Air Transp Manag. 2020;89:101903. https://doi.org/10.1016/j.jairtraman.2020.101903 .

Abdullah M, Hadzikadic M. Sentiment analysis of twitter data: emotions revealed regarding donald trump during the 2015–16 primary debates. 2017. https://doi.org/10.1109/ictai.2017.00120 .

Hoffmann T. ‘Too many Americans are trapped in fear, violence and poverty’: A psychology-informed sentiment analysis of campaign speeches from the 2016 US presidential election. Linguist Vanguard. 2018;4(1):1–9. https://doi.org/10.1515/lingvan-2017-0008 .

Giachanou A, Gonzalo J, Crestani F. Propagating sentiment signals for estimating reputation polarity. Inf Process Manag. 2019;56(6): 102079. https://doi.org/10.1016/j.ipm.2019.102079 .

Bose R, Aithal PS, Roy S. Sentiment analysis on the basis of tweeter comments of application of drugs by customary language toolkit and textblob opinions of distinct countries. Int J Emerg Trends Eng Res. 2020;8(7):3684–96. https://doi.org/10.30534/ijeter/2020/129872020 .

Muhammad A, Wiratunga N, Lothian R. Contextual sentiment analysis for social media genres. Knowledge-Based Syst. 2016;108:92–101. https://doi.org/10.1016/j.knosys.2016.05.032 .

Rodrigues RG, das Dores RM, Camilo-Junior CG, Rosa TC. SentiHealth-Cancer: a sentiment analysis tool to help detecting mood of patients in online social networks. Int J Med Inform. 2016;85(1):80–95. https://doi.org/10.1016/j.ijmedinf.2015.09.007 .

Severyn A, Moschitti A, Uryupina O, Plank B, Filippova K. Multi-lingual opinion mining on YouTube. Inf Process Manag. 2016;52(1):46–60. https://doi.org/10.1016/j.ipm.2015.03.002 .

Asghar MZ, Khan A, Zahra SR, Ahmad S, Kundi FM. Aspect-based opinion mining framework using heuristic patterns. Clust Comput. 2019;22:7181–99. https://doi.org/10.1007/s10586-017-1096-9 .

Giatsoglou M, Vozalis MG, Diamantaras K, Vakali A, Sarigiannidis G, Chatzisavvas KC. Sentiment analysis leveraging emotions and word embeddings. Expert Syst Appl. 2017;69:214–24. https://doi.org/10.1016/j.eswa.2016.10.043 .

Mahajan P, Rana A. Sentiment classification-how to quantify public emotions using twitter. Int J Sociotechnology Knowl Dev. 2018;10(1):57–71. https://doi.org/10.4018/IJSKD.2018010104 .

Chen B, Fan L, Fu X. Sentiment Classification of Tourism Based on Rules and {LDA} Topic Model. 2019. https://doi.org/10.1109/eei48997.2019.00108 .

Keyvanpour M, Karimi Zandian Z, Heidarypanah M. OMLML: a helpful opinion mining method based on lexicon and machine learning in social networks. Soc Netw Anal Min. 2020;10(1). https://doi.org/10.1007/s13278-019-0622-6 .

Hamad RA, Alqahtani SM, Torres MT. Emotion and polarity prediction from Twitter. 2017. https://doi.org/10.1109/sai.2017.8252118 .

Riaz S, Fatima M, Kamran M, Nisar MW. Opinion mining on large scale data using sentiment analysis and k-means clustering. Cluster Comput. 2019;22(s3):7149–64. https://doi.org/10.1007/s10586-017-1077-z .

Chowdhury SMMH, Ghosh P, Abujar S, Arina Afrin M, Akhter HS. Sentiment analysis of tweet data: the study of sentimental state of human from tweet text”. Adv Intell Syst Comput. 2019;813:3–14. https://doi.org/10.1007/978-981-13-1498-8_1 .

Tran YH, Tran QN. Estimating public opinion in social media content using aspect-based opinion mining. Lecture Notes of the Institute for Computer Sciences. Social Informatics and Telecommunications Engineering: Springer International Publishing; 2018. p. 101–15.

Google Scholar  

Meddeb I, Lavandier C, Kotzinos D. Using Twitter Streams for Opinion Mining: A Case Study on Airport Noise. In: Communications in Computer and Information Science, Springer International Publishing, 2020, pp. 145–160.

Madani Y, Erritali M, Bengourram J, Sailhan F. A hybrid multilingual fuzzy-based approach to the sentiment analysis problem using SentiWordNet. Int J Uncertainty Fuzz Knowl Based Syst. 2020;28(3):361–90. https://doi.org/10.1142/S0218488520500154 .

Gopi AP, Jyothi RNS, Narayana VL, Sandeep KS. Classification of tweets data based on polarity using improved RBF kernel of {SVM}. Int J Inf Technol. 2020. https://doi.org/10.1007/s41870-019-00409-4 .

Mandal L, Das R, Bhattacharya S, Basu PN. Intellimote: a hybrid classifier for classifying learners’ emotion in a distributed e-learning environment. Turkish J Electr Eng Comput Sci. 2017;25(3):2084–95. https://doi.org/10.3906/elk-1510-120 .

Van De Kauter M, Breesch D, Hoste V. Fine-grained analysis of explicit and implicit sentiment in financial news articles. Expert Syst Appl. 2015;42(11):4999–5010. https://doi.org/10.1016/j.eswa.2015.02.007 .

Sotirakou C, Germanakos P, Holzinger A, Mourlas C. Feedback Matters! Predicting the Appreciation of Online Articles A Data-Driven Approach. In: Lecture Notes in Computer Science. Springer International Publishing, 2018, pp. 147–159.

Ali F, Kwak D, Khan P, Islam SMR, Kim KH, Kwak KS. Fuzzy ontology-based sentiment analysis of transportation and city feature reviews for safe traveling. Transp Res Part C Emerg Technol. 2017;77:33–48. https://doi.org/10.1016/j.trc.2017.01.014 .

Noferesti S, Shamsfard M. Using Linked Data for polarity classification of patients’ experiences. J Biomed Inform. 2015;57:6–19. https://doi.org/10.1016/j.jbi.2015.06.017 .

Ahuja S, Dubey G. Clustering and sentiment analysis on Twitter data. 2017, https://doi.org/10.1109/tel-net.2017.8343568 .

Song C, Wang XK, Fei Cheng P, Qiang Wang J, Li L. SACPC: a framework based on probabilistic linguistic terms for short text sentiment analysis. Knowl Based Syst. 2020;194:105572. https://doi.org/10.1016/j.knosys.2020.105572 .

Vashishtha S, Susan S. Fuzzy rule based unsupervised sentiment analysis from social media posts. Expert Syst Appl. 2019;138: 112834. https://doi.org/10.1016/j.eswa.2019.112834 .

Derakhshan A, Beigy H. Sentiment analysis on stock social media for stock price movement prediction. Eng Appl Artif Intell. 2019;85:569–78. https://doi.org/10.1016/j.engappai.2019.07.002 .

Valdivia A, et al. Inconsistencies on TripAdvisor reviews: a unified index between users and sentiment analysis methods. Neurocomputing. 2019;353:3–16. https://doi.org/10.1016/j.neucom.2018.09.096 .

Jiang H, Kwong CK, Okudan Kremer GE, Park WY. Dynamic modelling of customer preferences for product design using DENFIS and opinion mining. Adv Eng Informatics. 2019;42:100969. https://doi.org/10.1016/j.aei.2019.100969 .

Wankhede R, Thakare AN. Design approach for accuracy in movies reviews using sentiment analysis. 2017. https://doi.org/10.1109/iceca.2017.8203652 .

Hiriyannaiah S, Siddesh GM, Srinivasa KG. Real-Time streaming data analysis using a three-Way classification method for sentimental analysis. Int J Inf Technol Web Eng. 2018;13(3):99–111. https://doi.org/10.4018/IJITWE.2018070107 .

Sahu TP, Ahuja S. Sentiment analysis of movie reviews: a study on feature selection and classification algorithms. 2016. https://doi.org/10.1109/microcom.2016.7522583 .

Lima ACES, De Castro LN, Corchado JM. A polarity analysis framework for Twitter messages. Appl Math Comput. 2015;270:756–67. https://doi.org/10.1016/j.amc.2015.08.059 .

Li Y, Fleyeh H. Twitter sentiment analysis of new {IKEA} stores using machine learning. 2018. https://doi.org/10.1109/comapp.2018.8460277 .

Ahmed S, Danti A. Effective sentimental analysis and opinion mining of web reviews using rule based classifiers. Adv Intell Syst Comput. 2016;410:171–9. https://doi.org/10.1007/978-81-322-2734-2_18 .

Vashishtha S, Susan S. Sentiment Cognition from Words Shortlisted by Fuzzy Entropy. IEEE Trans Cogn Dev Syst. 2020;12(3):541–50. https://doi.org/10.1109/TCDS.2019.2937796 .

Vashishtha S, Susan S. Highlighting keyphrases using senti-scoring and fuzzy entropy for unsupervised sentiment analysis. Expert Syst Appl. 2021;169: 114323. https://doi.org/10.1016/j.eswa.2020.114323 .

Sarkar K, Bhowmick M. Sentiment polarity detection in Bengali tweets using multinomial Naïve Bayes and support vector machines. 2017. https://doi.org/10.1109/calcon.2017.8280690 .

Rosli RM, Lokman AM, Aris SRS. Analysis of evoked emotions in extremist YouTube videos through Kansei evaluation. Adv Intell Syst Comput. 2018;739:740–7. https://doi.org/10.1007/978-981-10-8612-0_77 .

Yamada A, Hashimoto S, Nagata N. A text mining approach for automatic modeling of Kansei evaluation from review texts. Adv Intell Syst Comput. 2018;739:319–28. https://doi.org/10.1007/978-981-10-8612-0_34 .

Hsiao Y-H, Chen M-C, Lin M-K. Kansei Engineering with Online Review Mining for Hotel Service Development. 2017. https://doi.org/10.1109/iiai-aai.2017.12 .

Li Z, Tian ZG, Wang JW, Wang WM. Extraction of affective responses from customer reviews: an opinion mining and machine learning approach. Int J Comput Integr Manuf. 2020;33(7):670–85. https://doi.org/10.1080/0951192X.2019.1571240 .

Hsiao YH, Chen M-C. Kansei Engineering with Online Content Mining for Cross-Border Logistics Service Design. 2016. https://doi.org/10.1109/iiai-aai.2016.12 .

Asghar DM, Khan A, Bibi A, Kundi F, Ahmad H. Sentence-level emotion detection framework using rule-based classification. Cognit Comput. 2017;9:1–27. https://doi.org/10.1007/s12559-017-9503-3 .

Su Z, Yu S, Chu J, Zhai Q, Gong J, Fan H. A novel architecture: Using convolutional neural networks for Kansei attributes automatic evaluation and labeling. Adv Eng Informatics. 2020;44:101055.

Somayeh G. An investigation of the components of political developments on the national security of the Islamic Republic of Iran from the perspective of policy experts. J Polit Sci Public Aff. 2017;5(2). https://doi.org/10.4172/2332-0761.1000244 .

Fjäder C. The nation-state, national security and resilience in the age of globalisation. Resilience. 2014;2(2):114–29. https://doi.org/10.1080/21693293.2014.914771 .

Chandra S, Bhonsle R. National security: concept, measurement and management. Strateg Anal. 2015;39(4):337–59. https://doi.org/10.1080/09700161.2015.1047217 .

Muguruza CC. Human security as a policy framework: critics and challenges. Deusto J Hum Rights. 2017;4:15–35. https://doi.org/10.18543/aahdh-4-2007pp15-35 .

Teivans-Treinovskis J, Jefimovs N. State national security: aspect of recorded crime. J Secur Sustain Issues. 2012;2:41–8. https://doi.org/10.9770/jssi.2012.2.2(4) .

Hazel Kwon K, Raghav Rao H. Cyber-rumor sharing under a homeland security threat in the context of government Internet surveillance: the case of South-North Korea conflict. Gov Inf Q. 2017;34(2):307–16. https://doi.org/10.1016/j.giq.2017.04.002 .

Koujalagi DA, Thrupti NS, Kurbet K. Security threats in Indian cyberspace by social media and cyberhoaxes. Int J Trend Sci Res Dev. 2018;2(4):598–600. https://doi.org/10.31142/ijtsrd13040 .

Yassine M, Hajj H. A framework for emotion mining from text in online social networks. Proc. IEEE Int. Conf. Data Mining, ICDM, pp. 1136–1142, 2010. https://doi.org/10.1109/ICDMW.2010.75 .

Coan TG, Merolla JL, Zechmeister EJ, Zizumbo-Colunga D. Emotional responses shape the substance of information seeking under conditions of threat. Polit Res Q. 2020. https://doi.org/10.1177/1065912920949320 .

Lorenzoni I, Nicholson-Cole S, Whitmarsh L. Barriers perceived to engaging with climate change among the UK public and their policy implications. Glob Environ Chang. 2007;17(3–4):445–59. https://doi.org/10.1016/j.gloenvcha.2007.01.004 .

Nasir AFA, et al. Text-based emotion prediction system using machine learning approach. IOP Conf Ser Mater Sci Eng. 2020;769:12022. https://doi.org/10.1088/1757-899x/769/1/012022 .

Download references

Acknowledgements

This research is fully supported by the National Defence University of Malaysia (UPNM) and the Ministry of Higher Education Malaysia (MOHE) under FRGS/1/2021/ICT07/UPNM/02/1. The authors fully acknowledge UPNM and MOHE for the approved fund, which made this research viable and effective.

National Defence University of Malaysia (UPNM) under Grant FRGS/1/2021/ICT07/UPNM/02/1.

Author information

Authors and affiliations.

National Defence University of Malaysia, Kuala Lumpur, Malaysia

Noor Afiza Mat Razali, Nur Atiqah Malizan, Nor Asiakin Hasbullah, Muslihah Wook, Norulzahrah Mohd Zainuddin & Suzaimah Ramli

Management and Science University, Selangor, Malaysia

Khairul Khalil Ishak

CyberSecurity Malaysia, Selangor, Malaysia

Sazali Sukardi

You can also search for this author in PubMed   Google Scholar

Contributions

NAM conducted the systematic literature review and examined various techniques related to opinion mining and also took part in drafting the manuscript. NAMR wrote the first draft of the manuscript and introduced this topic to NAH, NMZ and MW. NAH, NMZ, MW has made significant contributions in discussing the structure of the review papers. KKI, SR and SS took part in reviewing the manuscript. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Noor Afiza Mat Razali .

Ethics declarations

Ethics approval and consent to participate.

Not applicable.

Consent for publication

Competing interests.

The authors declare that they have no competing interests.

Additional information

Publisher's note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ .

Reprints and permissions

About this article

Cite this article.

Razali, N.A.M., Malizan, N.A., Hasbullah, N.A. et al. Opinion mining for national security: techniques, domain applications, challenges and research opportunities. J Big Data 8 , 150 (2021). https://doi.org/10.1186/s40537-021-00536-5

Download citation

Received : 26 June 2021

Accepted : 08 November 2021

Published : 04 December 2021

DOI : https://doi.org/10.1186/s40537-021-00536-5

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

  • Opinion mining
  • Sentiment analysis
  • National security

opinion mining and sentiment analysis research papers

Help | Advanced Search

Computer Science > Computation and Language

Title: sentiment analysis and opinion mining on educational data: a survey.

Abstract: Sentiment analysis AKA opinion mining is one of the most widely used NLP applications to identify human intentions from their reviews. In the education sector, opinion mining is used to listen to student opinions and enhance their learning-teaching practices pedagogically. With advancements in sentiment annotation techniques and AI methodologies, student comments can be labelled with their sentiment orientation without much human intervention. In this review article, (1) we consider the role of emotional analysis in education from four levels: document level, sentence level, entity level, and aspect level, (2) sentiment annotation techniques including lexicon-based and corpus-based approaches for unsupervised annotations are explored, (3) the role of AI in sentiment analysis with methodologies like machine learning, deep learning, and transformers are discussed, (4) the impact of sentiment analysis on educational procedures to enhance pedagogy, decision-making, and evaluation are presented. Educational institutions have been widely invested to build sentiment analysis tools and process their student feedback to draw their opinions and insights. Applications built on sentiment analysis of student feedback are reviewed in this study. Challenges in sentiment analysis like multi-polarity, polysemous, negation words, and opinion spam detection are explored and their trends in the research space are discussed. The future directions of sentiment analysis in education are discussed.

Submission history

Access paper:.

  • Download PDF
  • Other Formats

license icon

References & Citations

  • Google Scholar
  • Semantic Scholar

BibTeX formatted citation

BibSonomy logo

Bibliographic and Citation Tools

Code, data and media associated with this article, recommenders and search tools.

  • Institution

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

opinion mining and sentiment analysis research papers

Academia.edu no longer supports Internet Explorer.

To browse Academia.edu and the wider internet faster and more securely, please take a few seconds to  upgrade your browser .

  •  We're Hiring!
  •  Help Center

OPINION MINING AND SENTIMENT ANALYSIS

  • Most Cited Papers
  • Most Downloaded Papers
  • Newest Papers
  • Save to Library
  • Last »
  • Opinion Mining (Data Mining) Follow Following
  • Sentiment Analysis Follow Following
  • Tablas Geotecnicas Follow Following
  • Green Consumer Behavior Follow Following
  • Parallel Corpora Follow Following
  • Energy Management Follow Following
  • Geotecnia Follow Following
  • Recommender Systems Follow Following
  • Natural Language Processing Follow Following
  • Mining Engineering Follow Following

Enter the email address you signed up with and we'll email you a reset link.

  • Academia.edu Publishing
  •   We're Hiring!
  •   Help Center
  • Find new research papers in:
  • Health Sciences
  • Earth Sciences
  • Cognitive Science
  • Mathematics
  • Computer Science
  • Academia ©2024
  • Skip to main content
  • Skip to primary sidebar
  • Skip to footer
  • QuestionPro

survey software icon

  • Solutions Industries Gaming Automotive Sports and events Education Government Travel & Hospitality Financial Services Healthcare Cannabis Technology Use Case NPS+ Communities Audience Contactless surveys Mobile LivePolls Member Experience GDPR Positive People Science 360 Feedback Surveys
  • Resources Blog eBooks Survey Templates Case Studies Training Help center

opinion mining and sentiment analysis research papers

Home Market Research

Opinion Mining: What it is, Types & Techniques to Follow

opinion mining

In a world where everyone’s voice is just a click away, understanding what people really think is a powerful skill. Businesses, researchers, and decision-makers have a secret weapon for this – opinion mining. But what exactly is it, and how does it work?

It is like a detective for emotions in the world of language. It focuses on extracting and analyzing opinions, sentiments, and subjective information from written or spoken words.

In this blog, we’ll break down what opinion mining is, explore its types, and discover the techniques that make it tick.

What is Opinion Mining?

Opinion mining, also known as sentiment analysis, is a field of natural language processing (NLP) that focuses on extracting and analyzing opinions, sentiments, and subjective information from written or spoken language. 

Opin mining aims to determine the attitude or emotional tone expressed in a text, whether positive, negative, or neutral. The process typically involves the following steps:

  • Text Collection
  • Pre-processing
  • Feature Extraction

Sentiment Analysis

  • Opinion Summarization

Opinion mining has practical applications in various fields, including business, marketing, customer service, and social media analysis. Companies use opinion mining to understand customer feedback, gauge public sentiment towards their products or services, and make informed decisions based on the insights obtained from analyzing opinions. 

It’s a valuable tool for businesses to manage their reputation, improve customer satisfaction, and stay competitive in the market.

Importance of Opinion Mining

Opinion mining holds significant importance in various fields because it can extract valuable insights from large amounts of textual data. Here are some key reasons why opinion mining is important:

Understanding the Customer Voice

Understanding what customers are saying about products and services is important. Opinion mining allows companies to tap into the customer’s voice by analyzing reviews, social media posts, and feedback. By deciphering sentiments, businesses can identify areas for improvement, enhance customer satisfaction, and stay ahead of the competition.

Shaping Brand Reputation

Your brand is not just what you say it is; it’s what your customers say about it. Opinion mining helps in brand reputation management by monitoring sentiments across social media platforms. This proactive approach allows businesses to address negative feedback promptly, preventing potential crises and preserving a positive brand image.

Guiding Product Development

Creating products that resonate with consumers is a perpetual challenge. Opinion mining provides a compass for product development by uncovering insights into what customers like or dislike about current offerings. Businesses can innovate and tailor products to meet market demands by prioritizing features based on customer preferences.

Informed Decision-Making

Businesses are bombarded with data every day, but opinion mining filters the noise and distills meaningful insights. Leaders can make informed decisions by considering the sentiments expressed in customer reviews, market trends, and social media conversations. This data-driven approach is crucial for staying agile and responsive to changing dynamics.

Enhancing Customer Support

Customer satisfaction is at the core of any successful business. Opinion mining contributes to this by providing a lens into customer support interactions. Businesses can enhance their support services by identifying and addressing issues highlighted in sentiments, ensuring a positive customer experience.

Opinion Mining vs Sentiment Analysis

Opinion mining and sentiment analysis are often used interchangeably, but they can have slightly different meanings depending on the context. In general, both terms refer to the process of extracting subjective information, opinions, and positive sentiment or negative sentiment from text. However, there are subtle distinctions between the two concepts:

Opinion Mining

Opinion mining is a broader term that encompasses the extraction of opinions, sentiments, emotions, and subjective information from text. It includes the identification of various aspects of opinions, such as opinions about features, aspects, entities, or events. It may involve analyzing the expressed sentiments’ strength, polarity, and subjectivity.

Opinion mining can be applied to different domains beyond sentiment analysis, including identifying preferences, beliefs, evaluations, and attitudes.

Sentiment analysis is a subset of opinion mining that focuses specifically on determining a text’s sentiment or emotional tone. It primarily categorizes text into positive, negative, or neutral sentiments. It’s a more narrow application of opinion mining that centers on understanding the emotional context of the expressed opinions.

Sentiment analysis is often used in business and marketing contexts to evaluate customer reviews, social media posts, and other textual data for overall sentiment.

Opinion mining is a broader umbrella term that encompasses the analysis of various subjective elements in the text, including sentiments, emotions, and opinions about different aspects. On the other hand, Sentiment analysis is a specific type of opinion mining that focuses specifically on determining whether the expressed sentiments are positive, negative, or neutral. 

While they share similarities, the key difference lies in the scope and depth of the analysis they perform within the realm of subjective information extraction.

Types of Opinion Mining

Opinion mining involves various types of analysis to extract and understand subjective information from text. The main types of opinion mining include:

1. Sentiment Analysis

Sentiment analysis focuses on categorizing opinions expressed in text as positive, negative, or neutral. It aims to determine the emotional tone of the text.

Commonly used in business and marketing to analyze customer reviews, social media posts, and other textual data for sentiment. Helps businesses understand public perception and make data-driven decisions.

2. Aspect-Based Sentiment Analysis (ABSA)

ABSA goes beyond overall sentiment analysis by identifying specific aspects or features within a piece of text and associating sentiments with each aspect. It is useful for understanding opinions about various product or service components. For example, in a restaurant review, ABSA might separately identify sentiments related to food quality, service, and ambiance.

3. Emotion Analysis

Emotion analysis aims to identify and categorize the emotions expressed in text, such as joy, anger, sadness, fear, or surprise. It is used in diverse fields, including customer service interactions, social media monitoring, and healthcare, to understand emotional responses and improve user experiences.

4. Opinion Summarization

Opinion summarization involves condensing a large number of opinions and reviews into a concise and informative summary. It helps businesses quickly grasp the overall sentiment and key points expressed in a set of reviews or opinions, facilitating decision-making.

5. Comparative Opinion Mining

Comparative opinion mining involves analyzing opinions that compare two or more entities, products, or concepts. It is commonly used in competitive analysis, marketing, and product development to understand how customers perceive different options and make informed comparisons.

6. Feature-Based Opinion Mining

Feature-based opinion mining focuses on identifying specific features, attributes, or components mentioned in the text and associating opinions with each feature. It is useful for product development and improvement by understanding which features users praise or criticize.

7. Multimodal Opinion Mining

Multimodal opinion mining involves analyzing opinions from multiple modalities, such as text, images, audio, or video. It enables a more comprehensive understanding of opinions by considering information from various sources, enhancing multimedia content analysis.t.

These types of opinion mining provide a nuanced understanding of subjective information in text, allowing businesses and researchers to extract valuable insights for decision-making and improvement. The choice of the specific type depends on the goals and context of the analysis.

 Opinion Mining Techniques

Opinion mining is a field of natural language processing techniques that focuses on extracting and analyzing opinions, sentiments, and emotions expressed in text. Here are some sentiment analysis techniques and best practices to follow in opinion mining:

Natural Language Processing (NLP)

Natural Language Processing is at the core of opinion mining. NLP techniques enable computers to understand, interpret, and generate human-like text. By employing tools like tokenization, part-of-speech tagging, and named entity recognition, NLP helps break down text into meaningful components, allowing for a more accurate analysis of sentiments.

Text Preprocessing

Before diving into sentiment analysis, it’s crucial to preprocess the text data. This involves removing stop words, punctuation, irrelevant symbols, and stemming or lemmatization to reduce words to their base form. Text preprocessing enhances the accuracy of sentiment analysis algorithms by simplifying the text while retaining its essential meaning.

Machine Learning Algorithms

Machine learning algorithms, particularly supervised learning techniques, are widely employed in opinion mining. These algorithms learn from labeled datasets, where each piece of text is associated with a sentiment label (positive, negative, or neutral). Popular machine learning algorithms for sentiment analysis include Support Vector Machines (SVM), Naive Bayes, and Decision Trees.

Lexicon-Based Approaches

Lexicon-based approaches rely on sentiment lexicons or dictionaries containing words annotated with corresponding sentiment polarity. These lexicons are pre-built and cover a vast range of words. Lexicon-based approaches can determine a positive or negative sentiment in a piece of text, and they can determine the overall sentiment. However, they may struggle with context-dependent sentiments and sarcasm.

Deep Learning Models

With the advancements in deep learning, neural networks have become powerful tools for sentiment analysis.

Recurrent Neural Networks (RNNs) and Long Short-Term Memory networks (LSTMs) are commonly used for sequence modeling tasks, making them suitable for analyzing textual data. Convolutional Neural Networks (CNNs) also effectively extract features from text for sentiment classification.

Opinion mining might sound like a big mystery, but with these simple techniques, it’s more like solving a fun puzzle. Clean up your text, find the special words, and let your computer friend learn. Dive into the world of opinions, and soon, you’ll be a pro at understanding what people really think!

Applications of Opinion Mining

Here, we’ll explore the simple yet powerful applications of opinion mining that profoundly impact various aspects of our digital lives.

1. Social Media Analysis

Monitoring and analyzing opinions expressed on social media platforms.

Utilizing machine learning tools to perform real-time sentiment analysis on social media mentions allows businesses to understand public sentiment, track brand mentions, and engage with customers.

2. Brand Awareness

Assessing public perception of a brand through sentiment analysis.

Analyzing news stories, blogs, social media, and forums to understand how the public perceives a brand. This helps track brand sentiment over time and make informed decisions to enhance brand image.

3. Customer Feedback

Analyzing opinions and sentiments expressed by customers about products or services.

Employing sentiment analysis tools to gather insights from customer feedback, reviews, surveys, and social media. This helps businesses understand customer satisfaction, identify areas for improvement, and enhance overall customer experience.

4. Customer Service

Evaluating sentiments in customer interactions to enhance service quality.

Using sentiment analysis to assess customer service communication through various channels like chatbots, emails, and support tickets. This allows businesses to maintain a consistent tone, address issues promptly, and improve overall customer service effectiveness.

5. Market Research

Analyzing opinions to identify market trends, preferences, and opportunities.

Employing sentiment analysis for market research to understand consumer opinions, identify emerging trends, and gain insights into competitive landscapes. This information helps in making informed business decisions and staying competitive.

6. Evaluating Marketing Campaigns

Assessing public reactions to marketing campaigns and advertisements.

Using real-time sentiment analysis to track and analyze sentiment related to marketing campaigns. This helps businesses understand the effectiveness of their campaigns, identify improvement areas, and adjust strategies based on customer feedback.

7. Crisis Management

Detecting and managing negative sentiments during potential crises.

Using a sentiment analysis system to monitor public sentiment during crises allows businesses to detect issues early and respond promptly. This aids in managing and mitigating the impact on brand reputation.

These opinion-mining applications empower businesses to leverage public opinions for strategic decision-making, customer engagement, and overall business improvement.

Ethical Considerations and Challenges

The field of opinion mining has become increasingly important. However, along with its benefits, sentiment analysis challenges need to be addressed. Let’s explore these issues in a simple way.

Privacy Concerns

Opinion mining often involves analyzing personal opinions, and sentiments expressed online. Respecting individuals’ privacy rights and ensuring that their data is handled responsibly is crucial. Researchers and businesses should be transparent about collecting and using this information, obtaining consent whenever necessary.

Biased Algorithms

Opinion mining algorithms can unintentionally reflect biases present in the data they are trained on. If the training data is biased, the algorithm’s results may also be biased. This is a challenge because biased opinions can lead to unfair or discriminatory outcomes. It’s essential to regularly evaluate and adjust algorithms to minimize bias and ensure fair representation.

Handling Sensitive Topics

Opinions often touch on sensitive subjects, and analyzing them requires careful consideration. Ethical opinion mining involves sensitively approaching topics like race, religion, and politics. Researchers should be aware of the potential impact of their analyses and strive to avoid contributing to the spread of misinformation or perpetuating stereotypes.

Consent and User Awareness

Users may not always be aware that their opinions are being collected and analyzed. It’s important for businesses and platforms to inform users about the purpose of opinion mining activities and give them the option to opt-out if they choose. Respecting user consent and providing clear information can help build trust.

Security of Data

Handling large amounts of data comes with the responsibility of ensuring its security. Opinion mining often involves processing vast datasets, and it’s crucial to implement robust security measures to protect this data from unauthorized access or breaches. Safeguarding user information should be a top priority.

How QuestionPro Can Help in Opinion Mining?

In an era where understanding public sentiment is crucial for businesses, researchers, and decision-makers, opinion mining has emerged as a powerful tool. One platform that stands out in facilitating effective opinion mining is QuestionPro. Let’s explore how QuestionPro can help in extracting valuable insights from the sea of public opinions.

1. Creating Surveys for Precision

At the heart of opinion mining lies the art of creating effective surveys. QuestionPro empowers users to create tailored surveys incorporating closed-ended and open-ended questions. This versatility allows for the collection of quantitative metrics and qualitative nuances, painting a comprehensive picture of opinions.

2. Simplifying Sentiment Analysis

Sorting through vast datasets can be daunting, but not with QuestionPro. Its built-in sentiment analysis tools streamline the process, categorizing responses into positive, negative, or neutral sentiments. This efficiency is a game-changer, particularly when dealing with large volumes of feedback.

3. Deeper Text Analytics

Uncovering insights from open-ended responses is made seamless through QuestionPro’s text analytics features. By identifying key phrases, sentiments, and recurring themes within textual data, users gain a deeper understanding of the context and emotions underlying opinions.

4. Exploring Social Media Insights

Recognizing the significance of social media in shaping opinions, QuestionPro seamlessly integrates with popular platforms. This ensures that surveys can tap into real-time conversations, allowing businesses and researchers to capture the pulse of public sentiments as they unfold.

5. Real-Time Reporting for Decision-Making

Time is of the essence in the digital age. With QuestionPro’s real-time reporting, users can monitor and analyze opinions as they pour in. This agility empowers decision-makers with timely insights, enabling them to adapt strategies based on current trends.

6. Visualizing Data for Clarity

Data, when presented visually, becomes more accessible and impactful. QuestionPro offers robust data visualization tools, allowing users to transform survey results into intuitive charts and graphs. This visual clarity enhances the communication of opinions within teams and to stakeholders.

7. Benchmarking for Contextual Insights

Context is key to understanding the significance of opinions. QuestionPro allows users to benchmark survey results against industry standards or past data, offering a contextual lens through which opinions can be evaluated and interpreted.

8. Advanced Analytics for Strategic Planning

QuestionPro provides advanced tools such as predictive analytics and machine learning algorithms for those seeking to push the boundaries of analysis. These tools uncover hidden patterns and trends, facilitating a deeper understanding of opinions and supporting strategic planning.

Opinion mining is a vital tool for businesses to extract valuable insights from public opinions. It helps in customer service, brand management, product development, and market research. The diverse types of opinion-mining techniques, from sentiment analysis to emotion analysis, provide complete insights for decision-making.

QuestionPro stands out as a platform offering tailored surveys, sentiment analysis tools, social media integration, and advanced analytics, empowering businesses to responsibly navigate and leverage public opinions. So, explore the world of opinions, and soon, you’ll be a pro at understanding what people think!

LEARN MORE         FREE TRIAL

MORE LIKE THIS

Customer Experience Management strategy

Customer Experience Management Strategy: A Complete Guide

Feb 21, 2024

customer experience framework

Customer Experience Framework: Building Exceptional Strategy

Feb 20, 2024

As much as anyone may understand about buyer personas which includes understanding their needs and purchasing authority, it is also vital to understand the path they will take towards the purchase

Want Someone To Listen? First Try to Understand — Tuesday CX Thoughts

5-point vs 7-point Likert scale

5-point vs 7-point Likert scale: Choosing the Best

Feb 19, 2024

Other categories

  • Academic Research
  • Artificial Intelligence
  • Assessments
  • Brand Awareness
  • Case Studies
  • Communities
  • Consumer Insights
  • Customer effort score
  • Customer Engagement
  • Customer Experience
  • Customer Loyalty
  • Customer Research
  • Customer Satisfaction
  • Employee Benefits
  • Employee Engagement
  • Employee Retention
  • Friday Five
  • General Data Protection Regulation
  • Insights Hub
  • Life@QuestionPro
  • Market Research
  • Mobile diaries
  • Mobile Surveys
  • New Features
  • Online Communities
  • Question Types
  • Questionnaire
  • QuestionPro Products
  • Release Notes
  • Research Tools and Apps
  • Revenue at Risk
  • Survey Templates
  • Training Tips
  • Uncategorized
  • Video Learning Series
  • What’s Coming Up
  • Workforce Intelligence

Advertisement

Advertisement

A review on sentiment analysis and emotion detection from text

  • Review Paper
  • Published: 28 August 2021
  • Volume 11 , article number  81 , ( 2021 )

Cite this article

  • Pansy Nandwani   ORCID: orcid.org/0000-0001-7544-5395 1 &
  • Rupali Verma 1  

50k Accesses

166 Citations

20 Altmetric

Explore all metrics

Social networking platforms have become an essential means for communicating feelings to the entire world due to rapid expansion in the Internet era. Several people use textual content, pictures, audio, and video to express their feelings or viewpoints. Text communication via Web-based networking media, on the other hand, is somewhat overwhelming. Every second, a massive amount of unstructured data is generated on the Internet due to social media platforms. The data must be processed as rapidly as generated to comprehend human psychology, and it can be accomplished using sentiment analysis, which recognizes polarity in texts. It assesses whether the author has a negative, positive, or neutral attitude toward an item, administration, individual, or location. In some applications, sentiment analysis is insufficient and hence requires emotion detection, which determines an individual’s emotional/mental state precisely. This review paper provides understanding into levels of sentiment analysis, various emotion models, and the process of sentiment analysis and emotion detection from text. Finally, this paper discusses the challenges faced during sentiment and emotion analysis.

Similar content being viewed by others

opinion mining and sentiment analysis research papers

A survey on sentiment analysis methods, applications, and challenges

Mayur Wankhade, Annavarapu Chandra Sekhara Rao & Chaitanya Kulkarni

opinion mining and sentiment analysis research papers

A survey and comparative study on negative sentiment analysis in social media data

Jayanta Paul, Ahel Das Chatterjee, … Jaya Sil

opinion mining and sentiment analysis research papers

Sentiment Analysis in Social Media Data for Depression Detection Using Artificial Intelligence: A Review

Nirmal Varghese Babu & E. Grace Mary Kanaga

Avoid common mistakes on your manuscript.

1 Introduction

Human language understanding and human language generation are the two aspects of natural language processing (NLP). The former, however, is more difficult due to ambiguities in natural language. However, the former is more challenging due to ambiguities present in natural language. Speech recognition, document summarization, question answering, speech synthesis, machine translation, and other applications all employ NLP (Itani et al. 2017 ). The two critical areas of natural language processing are sentiment analysis and emotion recognition. Even though these two names are sometimes used interchangeably, they differ in a few respects. Sentiment analysis is a means of assessing if data is positive, negative, or neutral.

In contrast, Emotion detection is a means of identifying distinct human emotion types such as furious, cheerful, or depressed. “Emotion detection,” “affective computing,” “emotion analysis,” and “emotion identification” are all phrases that are sometimes used interchangeably (Munezero et al. 2014 ). People are using social media to communicate their feelings since Internet services have improved. On social media, people freely express their feelings, arguments, opinions on wide range of topics. In addition, many users give feedbacks and reviews various products and services on various e-commerce sites. User's ratings and reviews on multiple platforms encourage vendors and service providers to enhance their current systems, goods, or services. Today almost every industry or company is undergoing some digital transition, resulting in vast amounts of structured and unstructured increase data. The enormous task for companies is to transform unstructured data into meaningful insights that can help them in decision-making (Ahmad et al. 2020 )

For instance, in the business world, vendors use social media platforms such as Instagram, YouTube, Twitter, and Facebook to broadcast information about their product and efficiently collect client feedback (Agbehadji and Ijabadeniyi 2021 ). People’s active feedback is valuable not only for business marketers to measure customer satisfaction and keep track of the competition but also for consumers who want to learn more about a product or service before buying it. Sentiment analysis assists marketers in understanding their customer's perspectives better so that they may make necessary changes to their products or services (Jang et al. 2013 ; Al Ajrawi et al. 2021 ). In both advanced and emerging nations, the impact of business and client sentiment on stock market performance may be witnessed. In addition, the rise of social media has made it easier and faster for investors to interact in the stock market. As a result, investor's sentiments impact their investment decisions which can swiftly spread and magnify over the network, and the stock market can be altered to some extent (Ahmed 2020 ). As a result, sentiment and emotion analysis has changed the way we conduct business (Bhardwaj et al. 2015 ).

In the healthcare sector, online social media like Twitter have become essential sources of health-related information provided by healthcare professionals and citizens. For example, people have been sharing their thoughts, opinions, and feelings on the Covid-19 pandemic (Garcia and Berton 2021 ). Patients were directed to stay isolated from their loved ones, which harmed their mental health. To save patients from mental health issues like depression, health practitioners must use automated sentiment and emotion analysis (Singh et al. 2021 ). People commonly share their feelings or beliefs on sites through their posts, and if someone seemed to be depressed, people could reach out to them to help, thus averting deteriorated mental health conditions.

Sentiment and emotion analysis plays a critical role in the education sector, both for teachers and students. The efficacy of a teacher is decided not only by his academic credentials but also by his enthusiasm, talent, and dedication. Taking timely feedback from students is the most effective technique for a teacher to improve teaching approaches (Sangeetha and Prabha 2020 ). Open-ended textual feedback is difficult to observe, and it is also challenging to derive conclusions manually. The findings of a sentiment analysis and emotion analysis assist teachers and organizations in taking corrective action. Since social site's inception, educational institutes are increasingly relying on social media like Facebook and Twitter for marketing and advertising purposes. Students and guardians conduct considerable online research and learn more about the potential institution, courses and professors. They use blogs and other discussion forums to interact with students who share similar interests and to assess the quality of possible colleges and universities. Thus, applying sentiment and emotion analysis can help the student to select the best institute or teacher in his registration process (Archana Rao and Baglodi 2017 ).

Sentiment and emotion analysis has a wide range of applications and can be done using various methodologies. There are three types of sentiment and emotion analysis techniques: lexicon based, machine learning based, and deep learning based. Each has its own set of benefits and drawbacks. Despite different sentiment and emotion recognition techniques, researchers face significant challenges, including dealing with context, ridicule, statements conveying several emotions, spreading Web slang, and lexical and syntactical ambiguity. Furthermore, because there are no standard rules for communicating feelings across multiple platforms, some express them with incredible effect, some stifle their feelings, and some structure their message logically. Therefore, it is a great challenge for researchers to develop a technique that can efficiently work in all domains.

In this review paper, Sect.  2 , introduces sentiment analysis and its various levels, emotion detection, and psychological models. Section  3 discusses multiple steps involved in sentiment and emotion analysis, including datasets, pre-processing of text, feature extraction techniques, and various sentiment and emotion analysis approaches. Section  4 addresses multiple challenges faced by researchers during sentiment and emotion analysis. Finally, Sect.  5 concludes the work.

2 Background

2.1 sentiment analysis.

Many people worldwide are now using blogs, forums, and social media sites such as Twitter and Facebook to share their opinions with the rest of the globe. Social media has become one of the most effective communication media available. As a result, an ample amount of data is generated, called big data, and sentiment analysis was introduced to analyze this big data effectively and efficiently (Nagamanjula and Pethalakshmi 2020 ). It has become exceptionally crucial for industry or organization to comprehend the sentiments of the user. Sentiment analysis, often known as opinion mining, is a method for detecting whether an author’s or user’s viewpoint on a subject is positive or negative. Sentiment analysis is defined as the process of obtaining meaningful information and semantics from text using natural processing techniques and determining the writer’s attitude, which might be positive, negative, or neutral (Onyenwe et al. 2020 ). Since the purpose of sentiment analysis is to determine polarity and categorize opinionated texts as positive or negative, dataset’s class range involved in sentiment analysis is not restricted to just positive or negative; it can be agreed or disagreed, good or bad. It can also be quantified on a 5-point scale: strongly disagree, disagree, neutral, agree, or strongly agree (Prabowo and Thelwall 2009 ). For instance, Ye et al. ( 2009 ) applied sentiment analysis on reviews on European and US destinations labeled on the scale of 1 to 5. They associated 1-star or 2-star reviews with the negative polarity and more than 2-star reviews with positive polarity. Gräbner et al. ( 2012 ) built a domain-specific lexicon that consists of tokens with their sentiment value. These tokens were gathered from customer reviews in the tourism domain to classify sentiment into 5-star ratings from terrible to excellent in the tourism domain. Moreover, Sentiment analysis from the text can be performed at three levels discussed in the following section. Salinca ( 2015 ) applied machine learning algorithms on the Yelp dataset, which contains reviews on service providers scaled from 1 to 5. Sentiment analysis can be categorized at three levels, mentioned in the following section.

2.1.1 Levels of sentiment analysis

Sentiment analysis is possible at three levels: sentence level, document level, and aspect level. At the sentence-level or phrase-level sentiment analysis, documents or paragraphs are broken down into sentences, and each sentence’s polarity is identified (Meena and Prabhakar 2007 ; Arulmurugan et al. 2019 ; Shirsat et al. 2019 ). At the document level, the sentiment is detected from the entire document or record (Pu et al. 2019 ). The necessity of document-level sentiment analysis is to extract global sentiment from long texts that contain redundant local patterns and lots of noise. The most challenging aspect of document-level sentiment classification is taking into account the link between words and phrases and the full context of semantic information to reflect document composition (Rao et al. 2018 ; Liu et al. 2020a ). It necessitates a deeper understanding of the intricate internal structure of sentiments and dependent words (Liu et al. 2020b ). At the aspect level, sentiment analysis, opinion about a specific aspect or feature is determined. For instance, the speed of the processor is high, but this product is overpriced. Here, speed and cost are two aspects or viewpoints. Speed is mentioned in the sentence hence called explicit aspect, whereas cost is an implicit aspect. Aspect-level sentiment analysis is a bit harder than the other two as implicit features are hard to identify. Devi Sri Nandhini and Pradeep ( 2020 ) proposed an algorithm to extract implicit aspects from documents based on the frequency of co-occurrence of aspect with feature indicator and by exploiting the relation between opinionated words and explicit aspects. Ma et al. ( 2019 ) took care of the two issues concerning aspect-level analysis: various aspects in a single sentence having different polarities and explicit position of context in an opinionated sentence. The authors built up a two-stage model based on LSTM with an attention mechanism to solve these issues. They proposed this model based on the assumption that context words near to aspect are more relevant and need greater attention than farther context words. At stage one, the model exploits multiple aspects in a sentence one by one with a position attention mechanism. Then, at the second state, it identifies (aspect, sentence) pairs according to the position of aspect and context around it and calculates the polarity of each team simultaneously.

As stated earlier, sentiment analysis and emotion analysis are often used interchangeably by researchers. However, they differ in a few ways. In sentiment analysis, polarity is the primary concern, whereas, in emotion detection, the emotional or psychological state or mood is detected. Sentiment analysis is exceptionally subjective, whereas emotion detection is more objective and precise. Section 2.2 describes all about emotion detection in detail.

2.2 Emotion detection

Emotions are an inseparable component of human life. These emotions influence human decision-making and help us communicate to the world in a better way. Emotion detection, also known as emotion recognition, is the process of identifying a person’s various feelings or emotions (for example, joy, sadness, or fury). Researchers have been working hard to automate emotion recognition for the past few years. However, some physical activities such as heart rate, shivering of hands, sweating, and voice pitch also convey a person’s emotional state (Kratzwald et al. 2018 ), but emotion detection from text is quite hard. In addition, various ambiguities and new slang or terminologies being introduced with each passing day make emotion detection from text more challenging. Furthermore, emotion detection is not just restricted to identifying the primary psychological conditions (happy, sad, anger); instead, it tends to reach up to 6-scale or 8-scale depending on the emotion model.

2.2.1 Emotion models/emotion theories

In English, the word 'emotion' came into existence in the seventeenth century, derived from the French word 'emotion, meaning a physical disturbance. Before the nineteenth century, passion, appetite, and affections were categorized as mental states. In the nineteenth century, the word 'emotion' was considered a psychological term (Dixon 2012 ). In psychology, complex states of feeling lead to a change in thoughts, actions, behavior, and personality referred to as emotions. Broadly, psychological or emotion models are classified into two categories: dimensional and categorical.

Dimensional Emotion model This model represents emotions based on three parameters: valence, arousal, and power (Bakker et al. 2014 . Valence means polarity, and arousal means how exciting a feeling is. For example, delighted is more exciting than happy. Power or dominance signifies restriction over emotion. These parameters decide the position of psychological states in 2-dimensional space, as illustrated in Fig. 1 .

figure 1

Dimensional model of emotions

Categorical Emotion model

In the categorical model, emotions are defined discretely, such as anger, happiness, sadness, and fear. Depending upon the particular categorical model, emotions are categorized into four, six, or eight categories.

Table  1 demonstrates numerous emotion models that are dimensional and categorical. In the realm of emotion detection, most researchers adopted Ekman and Plutchik’s emotion model. The emotional states defined by the models make up the set of labels used to annotate the sentences or documents. Batbaatar et al. ( 2019 ), Becker et al. ( 2017 ), Jain et al. ( 2017 ) adopted Ekman’s six basic emotions. Sailunaz and Alhajj ( 2019 ) used Ekman models for annotating tweets. Some researchers used customized emotion models by extending the model with one or two additional states. Roberts et al. ( 2012 ) used the Ekman model to annotate the tweets with the 'love' state. Ahmad et al. ( 2020 ) adopted the wheel of emotion modeled by Plutchik for labeling Hindi sentences with nine different Plutchik model states, decreasing semantic confusion, among other words. Plutchik and Ekman’s model's states are also utilized in various handcrafted lexicons like WordNet-Affect (Strapparava et al. 2004 ) and NRC (Mohammad and Turney 2013 ) word–emotion lexicons. Laubert and Parlamis ( 2019 ) referred to the Shaver model because of its three-level hierarchy structure of emotions. Valence or polarity is presented at the first level, followed by the second level consisting of five emotions, and the third level shows discrete 24 emotion states. Some researchers did not refer to any model and classified the dataset into three basic feelings: happy, sad, or angry.

Figure  2 depicts the numerous emotional states that can be found in various models. These states are plotted on a four-axis by taking the Plutchik model as a base model. The most commonly used emotion states in different models include anger, fear, joy, surprise, and disgust, as depicted in the figure above. It can be seen from the figure that emotions on two sides of the axis will not always be opposite of each other. For example, sadness and joy are opposites, but anger is not the opposite of fear.

figure 2

Illustration of various emotional models with some psychological states

3 Process of sentiment analysis and emotion detection

Process of sentiment analysis and emotion detection comes across various stages like collecting dataset, pre-processing, feature extraction, model development, and evaluation, as shown in Fig.  3 .

figure 3

Basic steps to perform sentiment analysis and emotion detection

3.1 Datasets for sentiment analysis and emotion detection

Table  2 lists numerous sentiment and emotion analysis datasets that researchers have used to assess the effectiveness of their models. The most common datasets are SemEval, Stanford sentiment treebank (SST), international survey of emotional antecedents and reactions (ISEAR) in the field of sentiment and emotion analysis. SemEval and SST datasets have various variants which differ in terms of domain, size, etc. ISEAR was collected from multiple respondents who felt one of the seven emotions (mentioned in the table) in some situations. The table shows that datasets include mainly the tweets, reviews, feedbacks, stories, etc. A dimensional model named valence, arousal dominance model (VAD) is used in the EmoBank dataset collected from news, blogs, letters, etc. Many studies have acquired data from social media sites such as Twitter, YouTube, and Facebook and had it labeled by language and psychology experts in the literature. Data crawled from various social media platform's posts, blogs, e-commerce sites are usually unstructured and thus need to be processed to make it structured to reduce some additional computations outlined in the following section.

3.2 Pre-processing of text

On social media, people usually communicate their feelings and emotions in effortless ways. As a result, the data obtained from these social media platform's posts, audits, comments, remarks, and criticisms are highly unstructured, making sentiment and emotion analysis difficult for machines. As a result, pre-processing is a critical stage in data cleaning since the data quality significantly impacts many approaches that follow pre-processing. The organization of a dataset necessitates pre-processing, including tokenization, stop word removal, POS tagging, etc. (Abdi et al. 2019 ; Bhaskar et al. 2015 ). Some of these pre-processing techniques can result in the loss of crucial information for sentiment and emotion analysis, which must be addressed.

Tokenization is the process of breaking down either the whole document or paragraph or just one sentence into chunks of words called tokens (Nagarajan and Gandhi 2019 ). For instance, consider the sentence “this place is so beautiful” and post-tokenization, it will become 'this,' "place," is, "so," beautiful.’ It is essential to normalize the text for achieving uniformity in data by converting the text into standard form, correcting the spelling of words, etc. (Ahuja et al. 2019 ).

Unnecessary words like articles and some prepositions that do not contribute toward emotion recognition and sentiment analysis must be removed. For instance, stop words like "is," "at," "an," "the" have nothing to do with sentiments, so these need to be removed to avoid unnecessary computations (Bhaskar et al. 2015 ; Abdi et al. 2019 ). POS tagging is the way to identify different parts of speech in a sentence. This step is beneficial in finding various aspects from a sentence that are generally described by nouns or noun phrases while sentiments and emotions are conveyed by adjectives (Sun et al. 2017 ).

Stemming and lemmatization are two crucial steps of pre-processing. In stemming, words are converted to their root form by truncating suffixes. For example, the terms "argued" and "argue" become "argue." This process reduces the unwanted computation of sentences (Kratzwald et al. 2018 ; Akilandeswari and Jothi 2018 ). Lemmatization involves morphological analysis to remove inflectional endings from a token to turn it into the base word lemma (Ghanbari-Adivi and Mosleh 2019 ). For instance, the term "caught" is converted into "catch" (Ahuja et al. 2019 ). Symeonidis et al. ( 2018 ) examined the performance of four machine learning models with a combination and ablation study of various pre-processing techniques on two datasets, namely SS-Tweet and SemEval. The authors concluded that removing numbers and lemmatization enhanced accuracy, whereas removing punctuation did not affect accuracy.

3.3 Feature extraction

The machine understands text in terms of numbers. The process of converting or mapping the text or words to real-valued vectors is called word vectorization or word embedding. It is a feature extraction technique wherein a document is broken down into sentences that are further broken into words; after that, the feature map or matrix is built. In the resulting matrix, each row represents a sentence or document while each feature column represents a word in the dictionary, and the values present in the cells of the feature map generally signify the count of the word in the sentence or document. To carry out feature extraction, one of the most straightforward methods used is 'Bag of Words' (BOW), in which a fixed-length vector of the count is defined where each entry corresponds to a word in a pre-defined dictionary of words. The word in a sentence is assigned a count of 0 if it is not present in the pre-defined dictionary, otherwise a count of greater than or equal to 1 depending on how many times it appears in the sentence. That is why the length of the vector is always equal to the words present in the dictionary. The advantage of this technique is its easy implementation but has significant drawbacks as it leads to a sparse matrix, loses the order of words in the sentence, and does not capture the meaning of a sentence (Bandhakavi et al. 2017 ; Abdi et al. 2019 ). For example, to represent the text “are you enjoying reading” from the pre-defined dictionary I, Hope, you, are, enjoying, reading would be (0,0,1,1,1,1). However, these representations can be improved by pre-processing of text and by utilizing n-gram, TF-IDF.

The N-gram method is an excellent option to resolve the order of words in sentence vector representation. In an n-gram vector representation, the text is represented as a collaboration of unique n-gram means groups of n adjacent terms or words. The value of n can be any natural number. For example, consider the sentence “to teach is to touch a life forever” and n = 3 called trigram will generate 'to teach is,' 'teach is to,' 'is to touch,' 'to touch a,' 'touch a life,' 'a life forever.' In this way, the order of the sentence can be maintained (Ahuja et al. 2019 ). N-grams features perform better than the BOW approach as they cover syntactic patterns, including critical information (Chaffar and Inkpen 2011 ). However, though n-gram maintains the order of words, it has high dimensionality and data sparsity (Le and Mikolov 2014 ).

Term frequency-inverse document frequency, usually abbreviated as TFIDF, is another method commonly used for feature extraction. This method represents text in matrix form, where each number quantifies how much information these terms carry in a given document. It is built on the premise that rare terms have much information in the text document (Liu et al. 2019 ). Term frequency is the number of times a word w appears in a document divided by the total number of words W in the document, and IDF is log (total number of documents (N) divided by the total number of documents in which word w appears (n)) (Songbo and Jin 2008 ). Ahuja et al. ( 2019 ) implemented six pre-processing techniques and compared two feature extraction techniques to identify the best approach. They applied six machine learning algorithms and used n-grams with n = 2 and TF-IDF for feature extraction over the SS-tweet dataset and concluded TF-IDF gives better performance over n-gram.

The availability of vast volumes of data allows a deep learning network to discover good vector representations. Feature extraction with word embedding based on neural networks is more informative. In neural network-based word embedding, the words with the same semantics or those related to each other are represented by similar vectors. This is more popular in word prediction as it retains the semantics of words. Google’s research team, headed by Tomas Mikolov, developed a model named Word2Vec for word embedding. With Word2Vec, it is possible to understand for a machine that “queen” + “female” + “male” vector representation would be the same as a vector representation of “king” (Souma et al. 2019 ).

Other examples of deep learning-based word embedding models include GloVe, developed by researchers at Stanford University, and FastText, introduced by Facebook. GloVe vectors are faster to train than Word2vec. FastText vectors have better accuracy as compared to Word2Vec vectors by several varying measures. Yang et al. ( 2018 ) proved that the choice of appropriate word embedding based on neural networks could lead to significant improvements even in the case of out of vocabulary (OOV) words. Authors compared various word embeddings, trained using Twitter and Wikipedia as corpora with TF-IDF word embedding.

3.4 Techniques for sentiment analysis and emotion detection

Figure  4 presents various techniques for sentiment analysis and emotion detection which are broadly classified into a lexicon-based approach, machine learning-based approach, deep learning-based approach. The hybrid approach is a combination of statistical and machine learning approaches to overcome the drawbacks of both approaches. Transfer learning is also a subset of machine learning which allows the use of the pre-trained model in other similar domain.

figure 4

Techniques for sentiment analysis and emotion detection

3.4.1 Sentiment analysis techniques

Lexicon-based approach This method maintains a word dictionary in which each positive and negative word is assigned a sentiment value. Then, the sum or mean of sentiment values is used to calculate the sentiment of the entire sentence or document. However, Jurek et al. ( 2015 ) tried a different approach called the normalization function to calculate the sentiment value more accurately than this basic summation and mean function. Dictionary-based approach and corpus-based approach are two types of lexicon-based approaches based on sentiment lexicon. In general, a dictionary maintains words of some language systemically, whereas a corpus is a random sample of text in some language. The exact meaning applies here in the dictionary-based approach and corpus-based approach. In the dictionary-based approach, a dictionary of seed words is maintained (Schouten and Frasincar 2015 ). To create this dictionary, the first small set of sentiment words, possibly with very short contexts like negations, is collected along with its polarity labels (Bernabé-Moreno et al. 2020 ). The dictionary is then updated by looking for their synonymous (words with the same polarity) and antonymous (words with opposite polarity). The accuracy of sentiment analysis via this approach will depend on the algorithm. However, this technique does not contain domain specificity. The Corpus-based approach solves the limitations of the dictionary-based approach by including domain-specific sentiment words where the polarity label is assigned to the sentiment word according to its context or domain. It is a data-driven approach where sentiment words along with context can be accessed. This approach can certainly be a rule-based approach with some NLP parsing techniques. Thus corpus-based approach tends to have poor generalization but can attain excellent performance within a particular domain. Since the dictionary-based approach does not consider the context around the sentiment word, it leads to less efficiency. Thus, Cho et al. ( 2014 ) explicitly handled the contextual polarity to make dictionaries adaptable in multiple domains with a data-driven approach. They took a three-step strategy: merge various dictionaries, remove the words that do not contribute toward classification, and switch the polarity according to a particular domain.

SentiWordNet (Esuli and Sebastiani 2006 ) and Valence Aware Dictionary and Sentiment Reasoner (VADER) (Hutto and Gilbert 2014 ) are popular lexicons in sentiment. Jha et al. ( 2018 ) tried to extend the lexicon application in multiple domains by creating a sentiment dictionary named Hindi Multi-Domain Sentiment Aware Dictionary (HMDSAD) for document-level sentiment analysis. This dictionary can be used to annotate the reviews into positive and negative. The proposed method labeled 24% more words than the traditional general lexicon Hindi Sentiwordnet (HSWN), a domain-specific lexicon. The semantic relationships between words in traditional lexicons have not been examined, improving sentiment classification performance. Based on this premise, Viegas et al. ( 2020 ) updated the lexicon by including additional terms after utilizing word embeddings to discover sentiment values for these words automatically. These sentiment values were derived from “nearby” word embeddings of already existing words in the lexicon.

Machine Learning-based approach There is another approach for sentiment analysis called the machine learning approach. The entire dataset is divided into two parts for training and testing purposes: a training dataset and a testing dataset. The training dataset is the information used to train the model by supplying the characteristics of different instances of an item. The testing dataset is then used to see how successfully the model from the training dataset has been trained. Generally, the machine learning algorithms used for sentiment analysis fall under supervised classification. Different kinds of algorithms required for sentiment classification may include Naïve Bayes, support vector machine (SVM), decision trees, etc. each having its pros and cons. Gamon ( 2004 ) applied a support vector machine over 40,884 customer feedbacks collected from surveys. The authors implemented various feature set combinations and achieved accuracy up to 85.47%. Ye et al. ( 2009 ) worked with SVM, N-gram model, and Naïve Bayes on sentiment and review on seven popular destinations of Europe and the USA, which was collected from yahoo.com. The authors achieved an accuracy of up to 87.17% with the n-gram model. indent Bučar et al. ( 2018 ) created the lexicon called JOB 1.0 and labeled news corpora called SentiNews 1.0 for sentiment analysis in Slovene texts. JOB 1.0 consists of 25,524 headwords extended with sentiment scaling from – 5 to 5 based on the AFINN model. For the construction of corpora, data were scraped from various news Web media. Then, after cleaning and pre-processing of data, the annotators were asked to annotate 10,427 documents on the 1–5 scale where one means negative and 5 means very positive. Then these documents were labeled with positive, negative, and neutral labels as per the specific average scale rating. The authors observed that Naïve Bayes performed better as compared to the support vector machine (SVM). Naive Bayes achieved an F1 score above 90% in binary classification and an F1 score above 60% for the three-class classification of sentiments. Tiwari et al. ( 2020 ) implemented three machine learning algorithms called SVM, Naive Bayes, and maximum entropy with the n-gram feature extraction method on the rotten tomato dataset. The training and testing dataset constituted 1600 reviews in each. The authors observed a decrease in accuracy with higher values of n in n-grams such as n = four, five, and six. Soumya and Pramod ( 2020 ) classified 3184 Malayalam tweets into positive and negative opinions using different feature vectors like BOW, Unigram with Sentiwordnet, etc. The authors implemented machine learning algorithms like random forest and Naïve Bayes and observed that the random forest with an accuracy of 95.6% performs better with Unigram Sentiwordnet considering negation words.

Deep Learning-based Approach In recent years, deep learning algorithms are dominating other traditional approaches for sentiment analysis. These algorithms detect the sentiments or opinions from text without doing feature engineering. There are multiple deep learning algorithms, namely recurrent neural network and convolutional neural networks, that can be applied to sentiment analysis and gives results that are more accurate than those provided by machine learning models. This approach makes humans free from constructing the features from text manually as deep learning models extract those features or patterns themselves. Jian et al. ( 2010 ) used a model based upon neural networks technology for categorizing sentiments which consisted of sentimental features, feature weight vectors, and prior knowledge base. The authors applied the model to review the data of Cornell movie. The experimental results of this paper revealed that the accuracy level of the I-model is extraordinary compared to HMM and SVM. Pasupa and Ayutthaya ( 2019 ) executed five-fold cross-validation on the children’s tale (Thai) dataset and compared three deep learning models called CNN, LSTM, and Bi-LSTM. These models are applied with or without features: POS-tagging (pre-processing technique to identify different parts of speech); Thai2Vec (word embedding trained from Thai Wikipedia); sentic (to understand the sentiment of the word). The authors observed the best performance in the CNN model with all the three features mentioned earlier. As stated earlier, social media platforms act as a significant source of data in the field of sentiment analysis. Data collected from this social sites consist lot of noise due to its free writing syle of users. Therefore, Arora and Kansal ( 2019 ) proposed a model named Conv-char-Emb that can handle the problem of noisy data and use small memory space for embedding. For embedding, convolution neural network (CNN) has been used that uses less parameters in feature representation. Dashtipour et al. ( 2020 ) proposed a deep learning framework to carry out sentiment analysis in the Persian language. The researchers concluded that deep neural networks such as LSTM and CNN outperformed the existing machine learning algorithms on the hotel and product review dataset.

Transfer Learning Approach and Hybrid Approach Transfer learning is also a part of machine learning. A model trained on large datasets to resolve one problem can be applied to other related issues. Re-using a pre-trained model on related domains as a starting point can save time and produce more efficient results. Zhang et al. ( 2012 ) proposed a novel instance learning method by directly modeling the distribution between different domains. Authors classified the dataset: Amazon product reviews and Twitter dataset into positive and negative sentiments. Tao and Fang ( 2020 ) proposed extending recent classification methods in aspect-based sentiment analysis to multi-label classification. The authors also developed transfer learning models called XLNet and Bert and evaluated the proposed approach on different datasets Yelp, wine reviews rotten tomato dataset from other domains. Deep learning and machine learning approaches yield good results, but the hybrid approach can give better results since it overcomes the limitations of each traditional model. Mladenović et al. ( 2016 ) proposed a feature reduction technique, a hybrid framework made of sentiment lexicon and Serbian wordnet. The authors expanded both lexicons by addition some morphological sentiment words to avoid loss of critical information while stemming. Al Amrani et al. ( 2018 ) compared their hybrid model made of SVM and random forest model, i.e., RFSVM, on amazon’s product reviews. The authors concluded RFSVM, with an accuracy level of 83.4%, performs better than SVM with 82.4% accuracy and random forest with 81% accuracy individually over the dataset of 1000 reviews. Alqaryouti et al. ( 2020 ) proposed the hybrid of the rule-based approach and domain lexicons for aspect-level sentiment detection to understand people’s opinions regarding government smart applications. The authors concluded that the proposed technique outperforms other lexicon-based baseline models by 5%. Ray and Chakrabarti ( 2020 ) combined the rule-based approach to extract aspects with a 7-layer deep learning CNN model to tag each aspect. The hybrid model achieved 87% accuracy, whereas the individual models had 75% accuracy with rule-based and 80% accuracy with the CNN model.

Table  3 describes various machine learning and deep learning algorithms used for analyzing sentiments in multiple domains. Many researchers implemented the proposed models on their dataset collected from Twitter and other social networking sites. The authors then compared their proposed models with other existing baseline models and different datasets. It is observed from the table above that accuracy by various models ranges from 80 to 90%.

3.4.2 Emotion detection techniques

Lexicon-based Approach Lexicon-based approach is a keyword-based search approach that searches for emotion keywords assigned to some psychological states (Rabeya et al. 2017 ). The popular lexicons for emotion detection are WordNet-Affect (Strapparava et al. 2004 and NRC word–emotion lexicon (Mohammad and Turney 2013 ). WordNet-Affect is an extended form of WordNet which consists of affective words annotated with emotion labels. NRC lexicon consists of 14,182 words, each assigned to one particular emotion and two sentiments. These lexicons are categorical lexicons that tag each word with an emotional state for emotion classification. However, by ignoring the intensity of emotions, these traditional lexicons become less informative and less adaptable. Thus, Li et al. ( 2021 ) suggested an effective strategy to obtain word-level emotion distribution to assign emotions with intensities to the sentiment words by merging a dimensional dictionary named NRC-Valence arousal dominance. EmoSenticNet (Poria et al. 2014 ) also consists of a large number assigned to both qualitative and quantitative labels. Generally, researchers generate their lexicons and directly apply them for emotion analysis, but lexicons can also be used for feature extraction purposes. Abdaoui et al. ( 2017 ) took the benefit of using online translation tools to create a French lexicon called FEEL (French expanded emotion lexicon) consisting of more than 14,000 words with both polarity and emotion labels. This lexicon was created by increasing the number of words in the NRC emotion lexicon and semi-automatic translation using six online translators. Those entries obtained from at least three translators were considered pre-validated and then validated by the manual translator. Bandhakavi et al. ( 2017 ) applied a domain-specific lexicon for the process of feature extraction in emotion analysis. The authors concluded that features derived from their proposed lexicon outperformed the other baseline features. Braun et al. ( 2021 ) constructed a multilingual corpus called MEmoFC, which stands for Multilingual Emotional Football Corpus, consisting of football reports from English, Dutch and German Web sites and match statistics crawled from Goal.com. The corpus was created by creating two metadata tables: one explaining details of a match like a date, place, participation teams, etc., and the second table consisted of abbreviations of football clubs. Authors demonstrated the corpus with various approaches to know the influence of the reports on game outcomes.

Machine Learning-based Techniques Emotion detection or classification may require different types of machine learning models such as Naïve Bayes, support vector machine, decision trees, etc. Jain et al. ( 2017 ) extracted the emotions from multilingual texts collected from three different domains. The authors used a novel approach called rich site summary for data collection and applied SVM and Naïve Bayes machine learning algorithms for emotion classification of twitter text. Results revealed that an accuracy level of 71.4% was achieved with the Naïve Bayes algorithm. Hasan et al. ( 2019 ) evaluated the machine learning algorithms like Naïve Bayes, SVM, and decision trees to identify emotions in text messages. The task is divided into two subtasks: Task 1 includes a collection of the dataset from Twitter and automatic labeling of the dataset using hashtags and model training. Task 2 is developing a two-stage EmotexStream that separates emotionless tweets at the first stage and identifies emotions in the text by utilizing the models trained in the task1. The authors observed accuracy of 90% in classifying emotions. Asghar et al. ( 2019 ) aimed to apply multiple machine learning models on the ISEAR dataset to find the best classifier. They found that the logistic regression model performed better than other classifiers with a recall value of 83%.

Deep Learning and Hybrid Technique Deep learning area is part of machine learning that processes information or signals in the same way as the human brain does. Deep learning models contain multiple layers of neurons. Thousands of neurons are interconnected to each other, which speeds up the processing in a parallel fashion. Chatterjee et al. ( 2019 ) developed a model called sentiment and semantic emotion detection (SSBED) by feeding sentiment and semantic representations to two LSTM layers, respectively. These representations are then concatenated and then passed to a mesh network for classification. The novel approach is based on the probability of multiple emotions present in the sentence and utilized both semantic and sentiment representation for better emotion classification. Results are evaluated over their own constructed dataset with tweet conversation pairs, and their model is compared with other baseline models. Xu et al. ( 2020 ) extracted features emotions using two-hybrid models named 3D convolutional-long short-term memory (3DCLS) and CNN-RNN from video and text, respectively. At the same time, the authors implemented SVM for audio-based emotion classification. Authors concluded results by fusing audio and video features at feature level with MKL fusion technique and further combining its results with text-based emotion classification results. It provides better accuracy than every other multimodal fusion technique, intending to analyze the sentiments of drug reviews written by patients on social media platforms. Basiri et al. ( 2020 ) proposed two models using a three-way decision theory. The first model is a 3-way fusion of one deep learning model with the traditional learning method (3W1DT), while the other model is a 3-way fusion of three deep learning models with the conventional learning method (3W3DT). The results derived using the Drugs.com dataset revealed that both frameworks performed better than traditional deep learning techniques. Furthermore, the performance of the first fusion model was noted to be much better as compared to the second model in regards to accuracy and F1-metric. In recent days, social media platforms are flooded with posts related to covid-19. Singh et al. ( 2021 ) applied emotion detection analysis on covid-19 tweets collected from the whole world and India only with Bidirectional Encoder Representations from Transformers (BERT) model on the Twitter data sets and achieved accuracy 94% approximately.

Transfer Learning Approach In traditional approaches, the common presumption is that the dataset is from the same domain; however, there is a need for a new model when the domain changes. The transfer learning approach allows you to reuse the existing pre-trained models in the target domain. For example, Ahmad et al. ( 2020 ) used a transfer learning technique due to the lack of resources for emotion detection in the Hindi language. The researchers pre-trained a model on two different English datasets: SemEval-2018, sentiment analysis, and one Hindi dataset with positive, neutral, conflict, and negative labels. They achieved a score of 0.53 f1 using the transfer learning and 0.47 using only base models CNN and Bi-LSTM with cross-lingual word embedding. Hazarika et al. ( 2020 ) created a TL-ERC model where the model was pre-trained over source multi-turn conversations and then transferred over emotion classification task on exchanged messages. The authors emphasized the issues like lack of labeled data in multi-conversations with the framework based on inductive transfer learning.

Table  4 shows that most researchers implemented models by combining machine learning and deep learning techniques with various feature extraction techniques. Most of the datasets are available in the English language. However, some researchers constructed the dataset of their regional language. For example, Sasidhar et al. ( 2020 ) created the dataset of Hindi-English code mixed with three basic emotions: happy, sad, and angry, and observed CNN-BILSTM gave better performance compared to others.

3.5 Model assessment

Finally, the model is compared with baseline models based on various parameters. There is a requirement of model evaluation metrics to quantify model performance. A confusion matrix is acquired, which provides the count of correct and incorrect judgments or predictions based on known actual values. This matrix displays true positive (TP), false negative (FN), false positive (FP), true negative (TN) values for data fitting based on positive and negative classes. Based on these values, researchers evaluated their model with metrics like accuracy, precision, and recall, F1 score, etc., mentioned in Table  5 .

4 Challenges in sentiment analysis and emotion analysis

In the Internet era, people are generating a lot of data in the form of informal text. Social networking sites present various challenges, as shown in Fig.  5 , which includes spelling mistakes, new slang, and incorrect use of grammar. These challenges make it difficult for machines to perform sentiment and emotion analysis. Sometimes individuals do not express their emotions clearly. For instance, in the sentence “Y have u been soooo late?”, 'why' is misspelled as 'y,' 'you' is misspelled as 'u,' and 'soooo' is used to show more impact. Moreover, this sentence does not express whether the person is angry or worried. Therefore, sentiment and emotion detection from real-world data is full of challenges due to several reasons (Batbaatar et al. 2019 ).

One of the challenges faced during emotion recognition and sentiment analysis is the lack of resources. For example, some statistical algorithms require a large annotated dataset. However, gathering data is not difficult, but manual labeling of the large dataset is quite time-consuming and less reliable (Balahur and Turchi 2014 ). The other problem regarding resources is that most of the resources are available in the English language. Therefore, sentiment analysis and emotion detection from a language other than English, primarily regional languages, are a great challenge and an opportunity for researchers. Furthermore, some of the corpora and lexicons are domain specific, which limits their re-use in other domains.

figure 5

Challenges in sentiment analysis and emotion detection

Another common problem is usually seen on Twitter, Facebook, and Instagram posts and conversations is Web slang. For example, the Young generation uses words like 'LOL,' which means laughing out loud to express laughter, 'FOMO,' which means fear of missing out, which says anxiety. The growing dictionary of Web slang is a massive obstacle for existing lexicons and trained models.

People usually express their anger or disappointment in sarcastic and irony sentences, which is hard to detect (Ghanbari-Adivi and Mosleh 2019 ). For instance, in the sentence, “This story is excellent to put you in sleep,” the excellent word signifies positive sentiment, but in actual the reviewer felt it quite dull. Therefore, sarcasm detection has become a tedious task in the field of sentiment and emotion detection.

The other challenge is the expression of multiple emotions in a single sentence. It is difficult to determine various aspects and their corresponding sentiments or emotions from the multi-opinionated sentence. For instance, the sentence “view at this site is so serene and calm, but this place stinks” shows two emotions, 'disgust' and 'soothing' in various aspects. Another challenge is that it is hard to detect polarity from comparative sentences. For example, consider two sentences 'Phone A is worse than phone B' and 'Phone B is worse than Phone A.' The word ’worse’ in both sentences will signify negative polarity, but these two sentences oppose each other (Shelke 2014 ).

5 Conclusion

In this paper, a review of the existing techniques for both emotion and sentiment detection is presented. As per the paper’s review, it has been analyzed that the lexicon-based technique performs well in both sentiment and emotion analysis. However, the dictionary-based approach is quite adaptable and straightforward to apply, whereas the corpus-based method is built on rules that function effectively in a certain domain. As a result, corpus-based approaches are more accurate but lack generalization. The performance of machine learning algorithms and deep learning algorithms depends on the pre-processing and size of the dataset. Nonetheless, in some cases, machine learning models fail to extract some implicit features or aspects of the text. In situations where the dataset is vast, the deep learning approach performs better than machine learning. Recurrent neural networks, especially the LSTM model, are prevalent in sentiment and emotion analysis, as they can cover long-term dependencies and extract features very well. But RNN with attention networks performs very well. At the same time, it is important to keep in mind that the lexicon-based approach and machine learning approach (traditional approaches) are also evolving and have obtained better outcomes. Also, pre-processing and feature extraction techniques have a significant impact on the performance of various approaches of sentiment and emotion analysis.

Abdaoui A, Azé J, Bringay S, Poncelet P (2017) Feel: a French expanded emotion lexicon. Lang Resour Eval 51(3):833–855

Article   Google Scholar  

Abdi A, Shamsuddin SM, Hasan S, Piran J (2019) Deep learning-based sentiment classification of evaluative text based on multi-feature fusion. Inf Process Manag 56(4):1245–1259

Adoma AF, Henry N-M, Chen W (2020) Comparative analyses of bert, roberta, distilbert, and xlnet for text-based emotion recognition. In: 2020 17th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP), IEEE, pp 117–121. https://doi.org/10.1109/ICCWAMTIP51612.2020.9317379

Agbehadji IE, Ijabadeniyi A (2021) Approach to sentiment analysis and business communication on social media. In: Fong S, Millham R (eds) Bio-inspired algorithms for data streaming and visualization, big data management, and fog computing, Springer Tracts in Nature-Inspired Computing. Springer, Singapore. https://doi.org/10.1007/978-981-15-6695-0_9

Agrawal A, An A (2012) Unsupervised emotion detection from text using semantic and syntactic relations. In: 2012 IEEE/WIC/ACM international conferences on web intelligence and intelligent agent technology, pp 346–353. https://doi.org/10.1109/WI-IAT.2012.170.

Ahmad Z, Jindal R, Ekbal A, Bhattachharyya P (2020) Borrow from rich cousin: transfer learning for emotion detection using cross lingual embedding. Expert Syst Appl 139:112851

Ahmed WM (2020) Stock market reactions to domestic sentiment: panel CS-ARDL evidence. Res Int Bus Finance 54:101240

Ahuja R, Chug A, Kohli S, Gupta S, Ahuja P (2019) The impact of features extraction on the sentiment analysis. Procedia Comput Sci 152:341–348

Akilandeswari J, Jothi G (2018) Sentiment classification of tweets with non-language features. Procedia Comput Sci 143:426–433

Al Ajrawi S, Agrawal A, Mangal H, Putluri K, Reid B, Hanna G, Sarkar M (2021) Evaluating business yelp’s star ratings using sentiment analysis. Materials Today: Proceedings. https://doi.org/10.1016/j.matpr.2020.12.137

Al Amrani Y, Lazaar M, El Kadiri KE (2018) Random forest and support vector machine based hybrid approach to sentiment analysis. Procedia Comput Sci 127:511–520

Alqaryouti O, Siyam N, Monem AA, Shaalan K (2020) Aspect-based sentiment analysis using smart government review data. Appl Comput Inf. https://doi.org/10.1016/j.aci.2019.11.003

Alswaidan N, Menai MEB (2020) A survey of state-of-the-art approaches for emotion recognition in text. Knowl Inf Syst 62(8):1–51

Archana Rao PN, Baglodi K (2017) Role of sentiment analysis in education sector in the era of big data: a survey. Int J Latest Trends Eng Technol 22–24

Arora M, Kansal V (2019) Character level embedding with deep convolutional neural network for text normalization of unstructured data for twitter sentiment analysis. Soc Netw Anal Min 9(1):1–14

Arulmurugan R, Sabarmathi K, Anandakumar H (2019) Classification of sentence level sentiment analysis using cloud machine learning techniques. Cluster Comput 22(1):1199–1209

Asghar MZ, Subhan F, Imran M, Kundi FM, Shamshirband S, Mosavi A, Csiba P, Várkonyi-Kóczy AR (2019) Performance evaluation of supervised machine learning techniques for efficient detection of emotions from online content. arXiv preprint arXiv:190801587

Bakker I, Van Der Voordt T, Vink P, De Boon J (2014) Pleasure, arousal, dominance: Mehrabian and Russell revisited. Curr Psychol 33(3):405–421

Balahur A, Turchi M (2014) Comparative experiments using supervised learning and machine translation for multilingual sentiment analysis. Comput Speech Lang 28(1):56–75

Bandhakavi A, Wiratunga N, Padmanabhan D, Massie S (2017) Lexicon based feature extraction for emotion text classification. Pattern Recogn Lett 93:133–142

Basiri ME, Abdar M, Cifci MA, Nemati S, Acharya UR (2020) A novel method for sentiment classification of drug reviews using fusion of deep and machine learning techniques. Knowl Based Syst 198:105949

Batbaatar E, Li M, Ryu KH (2019) Semantic-emotion neural network for emotion recognition from text. IEEE Access 7:111866–111878

Becker K, Moreira VP, dos Santos AG (2017) Multilingual emotion classification using supervised learning: comparative experiments. Inf Process Manag 53(3):684–704

Bernabé-Moreno J, Tejeda-Lorente A, Herce-Zelaya J, Porcel C, Herrera-Viedma E (2020) A context-aware embeddings supported method to extract a fuzzy sentiment polarity dictionary. Knowl-Based Syst 190:105236

Bhardwaj A, Narayan Y, Dutta M et al (2015) Sentiment analysis for Indian stock market prediction using sensex and nifty. Procedia Comput Sci 70:85–91

Bhaskar J, Sruthi K, Nedungadi P (2015) Hybrid approach for emotion classification of audio conversation based on text and speech mining. Procedia Comput Sci 46:635–643

Braun N, van der Lee C, Gatti L, Goudbeek M, Krahmer E (2021) Memofc: introducing the multilingual emotional football corpus. Lang Resour Eval 55(2):389–430

Bučar J, Žnidaršič M, Povh J (2018) Annotated news corpora and a lexicon for sentiment analysis in Slovene. Lang Resour Eval 52(3):895–919

Buechel S, Hahn U (2017) Emobank: Studying the impact of annotation perspective and representation format on dimensional emotion analysis. In: Proceedings of the 15th conference of the european chapter of the association for computational linguistics: volume 2, Short Papers, pp 578–585

Chaffar S, Inkpen D (2011) Using a heterogeneous dataset for emotion analysis in text. In: Butz C, Lingras P (eds) Advances in artificial intelligence. Canadian AI 2011. Lecture notes in computer science, vol 6657. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21043-3_8

Chatterjee A, Gupta U, Chinnakotla MK, Srikanth R, Galley M, Agrawal P (2019) Understanding emotions in text using deep learning and big data. Comput Hum Behav 93:309–317

Chen T, Xu R, He Y, Wang X (2017) Improving sentiment analysis via sentence type classification using BILSTM-CRF and CNN. Expert Syst Appl 72:221–230

Cho H, Kim S, Lee J, Lee JS (2014) Data-driven integration of multiple sentiment dictionaries for lexicon-based sentiment classification of product reviews. Knowl-Based Syst 71:61–71

Chowanda A, Sutoyo R, Tanachutiwat S et al (2021) Exploring text-based emotions recognition machine learning techniques on social media conversation. Procedia Comput Sci 179:821–828

Dahou A, Xiong S, Zhou J, Haddoud MH, Duan P (2016) Word embeddings and convolutional neural network for arabic sentiment classification. In: Proceedings of coling 2016, the 26th international conference on computational linguistics: Technical papers, pp 2418–2427

Dashtipour K, Gogate M, Li J, Jiang F, Kong B, Hussain A (2020) A hybrid Persian sentiment analysis framework: integrating dependency grammar based rules and deep neural networks. Neurocomputing 380:1–10

Devi Sri Nandhini M, Pradeep G (2020) A hybrid co-occurrence and ranking-based approach for detection of implicit aspects in aspect-based sentiment analysis. SN Comput Sci 1:1–9

Dheeraj K, Ramakrishnudu T (2021) Negative emotions detection on online mental-health related patients texts using the deep learning with MHA-BCNN model. Expert Syst Appl 182:115265

Dixon T (2012) “Emotion”: the history of a keyword in crisis. Emot Rev 4(4):338–344

Ekman P (1992) An argument for basic emotions. Cognit Emot 6(3–4):169–200

Esuli A, Sebastiani F (2006) Sentiwordnet: a publicly available lexical resource for opinion mining. LREC, Citeseer 6:417–422

Google Scholar  

Gamon M (2004) Sentiment classification on customer feedback data: noisy data, large feature vectors, and the role of linguistic analysis. In: COLING 2004: Proceedings of the 20th international conference on computational linguistics, pp 841–847

Garcia K, Berton L (2021) Topic detection and sentiment analysis in twitter content related to covid-19 from brazil and the USA. Appl Soft Comput 101:107057

Ghanbari-Adivi F, Mosleh M (2019) Text emotion detection in social networks using a novel ensemble classifier based on Parzen tree estimator (tpe). Neural Comput Appl 31(12):8971–8983

Goularas D, Kamis S (2019) Evaluation of deep learning techniques in sentiment analysis from twitter data. In: 2019 International conference on deep learning and machine learning in emerging applications (Deep-ML), IEEE, pp 12–17

Gräbner D, Zanker M, Fliedl G, Fuchs M, et al. (2012) Classification of customer reviews based on sentiment analysis. In: ENTER, Citeseer, pp 460–470

Hasan M, Rundensteiner E, Agu E (2014) Emotex: detecting emotions in twitter messages. In: 2014 ASE BIGDATA/SOCIALCOM/CYBERSECURITY Conference. Stanford University, Academy of Science and Engineering (ASE), USA, ASE, pp 1–10

Hasan M, Rundensteiner E, Agu E (2019) Automatic emotion detection in text streams by analyzing twitter data. Int J Data Sci Anal 7(1):35–51

Hazarika D, Poria S, Zimmermann R, Mihalcea R (2020) Conversational transfer learning for emotion recognition. Inf Fusion 65:1–12

Hosseini AS (2017) Sentence-level emotion mining based on combination of adaptive meta-level features and sentence syntactic features. Eng Appl Artif Intell 65:361–374

Hutto C, Gilbert E (2014) Vader: a parsimonious rule-based model for sentiment analysis of social media text. In: Proceedings of the international AAAI conference on web and social media, vol 8

Itani M, Roast C, Al-Khayatt S (2017) Developing resources for sentiment analysis of informal Arabic text in social media. Procedia Comput Sci 117:129–136

Izard CE (1992) Basic emotions, relations among emotions, and emotion-cognition relations. Psychol Rev 99(3):561–565

Jain VK, Kumar S, Fernandes SL (2017) Extraction of emotions from multilingual text using intelligent text processing and computational linguistics. J Comput Sci 21:316–326

Jang HJ, Sim J, Lee Y, Kwon O (2013) Deep sentiment analysis: mining the causality between personality-value-attitude for analyzing business ads in social media. Expert Syst Appl 40(18):7492–7503

Jha V, Savitha R, Shenoy PD, Venugopal K, Sangaiah AK (2018) A novel sentiment aware dictionary for multi-domain sentiment classification. Comput Electr Eng 69:585–597

Jian Z, Chen X, Wang Hs (2010) Sentiment classification using the theory of ANNs. J China Univ Posts Telecommun 17:58–62

Jurek A, Mulvenna MD, Bi Y (2015) Improved lexicon-based sentiment analysis for social media analytics. Secur Inform 4(1):1–13

Kratzwald B, Ilić S, Kraus M, Feuerriegel S, Prendinger H (2018) Deep learning for affective computing: text-based emotion recognition in decision support. Decis Support Syst 115:24–35

Laubert C, Parlamis J (2019) Are you angry (happy, sad) or aren’t you? Emotion detection difficulty in email negotiation. Group Decis Negot 28(2):377–413

Le Q, Mikolov T (2014) Distributed representations of sentences and documents. In: International conference on machine learning, pp 1188–1196

Li Z, Xie H, Cheng G, Li Q (2021) Word-level emotion distribution with two schemas for short text emotion classification. Knowledge-Based Syst 227:107163

Liu Y, Wan Y, Su X (2019) Identifying individual expectations in service recovery through natural language processing and machine learning. Expert Syst Appl 131:288–298

Liu F, Zheng J, Zheng L, Chen C (2020a) Combining attention-based bidirectional gated recurrent neural network and two-dimensional convolutional neural network for document-level sentiment classification. Neurocomputing 371:39–50

Liu S, Lee K, Lee I (2020b) Document-level multi-topic sentiment classification of email data with bilstm and data augmentation. Knowl-Based Syst 197:105918

Lövheim H (2012) A new three-dimensional model for emotions and monoamine neurotransmitters. Med Hypoth 78(2):341–348

Ma X, Zeng J, Peng L, Fortino G, Zhang Y (2019) Modeling multi-aspects within one opinionated sentence simultaneously for aspect-level sentiment analysis. Future Gener Comput Syst 93:304–311

Meena A, Prabhakar TV (2007) Sentence level sentiment analysis in the presence of conjuncts using linguistic analysis. In: Amati G, Carpineto C, Romano G (eds) Advances in information retrieval. ECIR 2007. Lecture notes in computer science, vol 4425. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-71496-5_53

Mladenović M, Mitrović J, Krstev C, Vitas D (2016) Hybrid sentiment analysis framework for a morphologically rich language. J Intell Inf Syst 46(3):599–620

Mohammad SM, Turney PD (2013) Crowdsourcing a word-emotion association lexicon. Comput Intell 29(3):436–465

Article   MathSciNet   Google Scholar  

Moraes R, Valiati JF, Gavião Neto WP (2013) Document-level sentiment classification: an empirical comparison between SVM and ANN. Expert Syst Appl 40(2):621–633

Mukherjee P, Badr Y, Doppalapudi S, Srinivasan SM, Sangwan RS, Sharma R (2021) Effect of negation in sentences on sentiment analysis and polarity detection. Procedia Comput Sci 185:370–379

Munezero M, Montero CS, Sutinen E, Pajunen J (2014) Are they different? affect, feeling, emotion, sentiment, and opinion detection in text. IEEE Trans Affect Comput 5(2):101–111

Nagamanjula R, Pethalakshmi A (2020) A novel framework based on bi-objective optimization and lan 2 fis for twitter sentiment analysis. Soc Netw Anal Min 10:1–16

Nagarajan SM, Gandhi UD (2019) Classifying streaming of twitter data based on sentiment analysis using hybridization. Neural Comput Appl 31(5):1425–1433

Nandal N, Tanwar R, Pruthi J (2020) Machine learning based aspect level sentiment analysis for amazon products. Spat Inf Res 28(5):601–607

Onyenwe I, Nwagbo S, Mbeledogu N, Onyedinma E (2020) The impact of political party/candidate on the election results from a sentiment analysis perspective using# anambradecides2017 tweets. Soc Netw Anal Min 10(1):1–17

Pasupa K, Ayutthaya TSN (2019) Thai sentiment analysis with deep learning techniques: a comparative study based on word embedding, pos-tag, and sentic features. Sustain Cities Soc 50:101615

Plutchik R (1982) A psychoevolutionary theory of emotions. https://doi.org/10.1177/053901882021004003

Poria S, Gelbukh A, Cambria E, Hussain A, Huang GB (2014) Emosenticspace: a novel framework for affective common-sense reasoning. Knowl-Based Syst 69:108–123

Prabowo R, Thelwall M (2009) Sentiment analysis: a combined approach. J Inform 3(2):143–157

Pu X, Wu G, Yuan C (2019) Exploring overall opinions for document level sentiment classification with structural SVM. Multim Syst 25(1):21–33

Rabeya T, Ferdous S, Ali HS, Chakraborty NR (2017) A survey on emotion detection: a lexicon based backtracking approach for detecting emotion from Bengali text. In: 2017 20th international conference of computer and information technology (ICCIT), IEEE, pp 1–7

Rao G, Huang W, Feng Z, Cong Q (2018) LSTM with sentence representations for document-level sentiment classification. Neurocomputing 308:49–57

Ray P, Chakrabarti A (2020) A mixed approach of deep learning method and rule-based method to improve aspect level sentiment analysis. Appl Comput Inform

Roberts K, Roach MA, Johnson J, Guthrie J, Harabagiu SM (2012) Empatweet: annotating and detecting emotions on twitter. Lrec, Citeseer 12:3806–3813

Russell JA (1980) A circumplex model of affect. J Pers Soc Psychol 39(6):1161

Sailunaz K, Alhajj R (2019) Emotion and sentiment analysis from twitter text. J Comput Sci 36:101003

Salinca A (2015) Business reviews classification using sentiment analysis. In: Proceedings of the 2015 17th international symposium on symbolic and numeric algorithms for scientific computing (SYNASC), IEEE, pp 247–250

Sangeetha K, Prabha D (2020) Sentiment analysis of student feedback using multi-head attention fusion model of word and context embedding for LSTM. J Ambient Intell Hum Comput 12:4117–4126

Sasidhar TT, Premjith B, Soman K (2020) Emotion detection in hinglish (hindi+ english) code-mixed social media text. Procedia Comput Sci 171:1346–1352

Schouten K, Frasincar F (2015) Survey on aspect-level sentiment analysis. IEEE Trans Knowl Data Eng 28(3):813–830

Seal D, Roy UK, Basak R (2020) Sentence-level emotion detection from text based on semantic rules. In: Information and communication technology for sustainable development. Springer, pp 423–430

Shamantha RB, Shetty SM, Rai P (2019) Sentiment analysis using machine learning classifiers: evaluation of performance. In: Proceedings of the 2019 IEEE 4th international conference on computer and communication systems (ICCCS), IEEE, pp 21–25

Sharma P, Sharma A (2020) Experimental investigation of automated system for twitter sentiment analysis to predict the public emotions using machine learning algorithms. Mater Today Proc

Shaver P, Schwartz J, Kirson D, O’connor C (1987) Emotion knowledge: further exploration of a prototype approach. J Pers Soc Psychol 52(6):1061

Shelke NM (2014) Approaches of emotion detection from text. Int J Comput Sci Inf Technol 2(2):123–128

Shirsat VS, Jagdale RS, Deshmukh SN (2019) Sentence level sentiment identification and calculation from news articles using machine learning techniques. In: Computing, communication and signal processing. Springer, pp 371–376

Shrivastava K, Kumar S, Jain DK (2019) An effective approach for emotion detection in multimedia text data using sequence based convolutional neural network. Multim Tools Appl 78(20):29607–29639

Singh M, Jakhar AK, Pandey S (2021) Sentiment analysis on the impact of coronavirus in social life using the Bert model. Soc Netw Anal Min 11(1):1–11

Songbo T, Jin Z (2008) An empirical study of sentiment analysis for Chinese documents. Expert Syst Appl 34(4):2622–2629

Souma W, Vodenska I, Aoyama H (2019) Enhanced news sentiment analysis using deep learning methods. J Comput Soc Sci 2(1):33–46

Soumya S, Pramod KV (2020) Sentiment analysis of malayalam tweets using machine learning techniques. ICT Express 6(4):300–305

Strapparava C, Valitutti A, et al. (2004) Wordnet affect: an affective extension of wordnet. In: Lrec, Citeseer, vol 4, pp 1083–1086

Sun S, Luo C, Chen J (2017) A review of natural language processing techniques for opinion mining systems. Inf Fusion 36:10–25

Symeonidis S, Effrosynidis D, Arampatzis A (2018) A comparative evaluation of pre-processing techniques and their interactions for twitter sentiment analysis. Expert Syst Appl 110:298–310

Tang D, Qin B, Liu T (2015) Learning semantic representations of users and products for document level sentiment classification. In: Proceedings of the 53rd annual meeting of the association for computational linguistics and the 7th international joint conference on natural language processing (Volume 1: Long Papers), pp 1014–1023

Tao J, Fang X (2020) Toward multi-label sentiment analysis: a transfer learning based approach. J Big Data 7(1):1–26

Tiwari P, Mishra BK, Kumar S, Kumar V (2020) Implementation of n-gram methodology for rotten tomatoes review dataset sentiment analysis. In: Cognitive analytics: concepts, methodologies, tools, and applications, IGI Global, pp 689–701

Tomkins SS, McCarter R (1964) What and where are the primary affects? Some evidence for a theory. Percept Mot Skills 18(1):119–158

Untawale TM, Choudhari G (2019) Implementation of sentiment classification of movie reviews by supervised machine learning approaches. In: Proceedings of the 2019 3rd international conference on computing methodologies and communication (ICCMC), IEEE, pp 1197–1200

Viegas F, Alvim MS, Canuto S, Rosa T, Gonçalves MA, Rocha L (2020) Exploiting semantic relationships for unsupervised expansion of sentiment lexicons. Inf Syst 94:101606

Xu G, Li W, Liu J (2020) A social emotion classification approach using multi-model fusion. Future Gen Comput Syst 102:347–356

Yang X, Macdonald C, Ounis I (2018) Using word embeddings in twitter election classification. Inf Retriev J 21(2–3):183–207

Ye Q, Zhang Z, Law R (2009) Sentiment classification of online reviews to travel destinations by supervised machine learning approaches. Expert Syst Appl 36(3):6527–6535

Zhang D, Si L, Rego VJ (2012) Sentiment detection with auxiliary data. Inf Retriev 15(3–4):373–390

Download references

Author information

Authors and affiliations.

Computer Science and Engineering Department, Punjab Engineering College, Chandigarh, India

Pansy Nandwani & Rupali Verma

You can also search for this author in PubMed   Google Scholar

Corresponding authors

Correspondence to Pansy Nandwani or Rupali Verma .

Additional information

Publisher's note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Nandwani, P., Verma, R. A review on sentiment analysis and emotion detection from text. Soc. Netw. Anal. Min. 11 , 81 (2021). https://doi.org/10.1007/s13278-021-00776-6

Download citation

Received : 06 April 2021

Revised : 25 June 2021

Accepted : 10 July 2021

Published : 28 August 2021

DOI : https://doi.org/10.1007/s13278-021-00776-6

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

  • Affective computing
  • Natural language processing
  • Opinion mining
  • Pre-processing
  • Word embedding
  • Find a journal
  • Publish with us
  • Track your research

This paper is in the following e-collection/theme issue:

Published on 14.2.2024 in Vol 26 (2024)

Correction: Public Opinion About COVID-19 on a Microblog Platform in China: Topic Modeling and Multidimensional Sentiment Analysis of Social Media

Authors of this article:

Author Orcid Image

There are no citations yet available for this article according to Crossref .

IMAGES

  1. (PDF) Opinion mining and sentiment analysis

    opinion mining and sentiment analysis research papers

  2. (PDF) Opinion Mining, Sentiment Analysis and Emotion Understanding in

    opinion mining and sentiment analysis research papers

  3. (PDF) Sentiment analysis and opinion mining applied to scientific paper

    opinion mining and sentiment analysis research papers

  4. (PDF) Opinion Mining on Social Media Data: Sentiment Analysis of User

    opinion mining and sentiment analysis research papers

  5. (PDF) A Multi-Classifier System for Sentiment Analysis and Opinion Mining

    opinion mining and sentiment analysis research papers

  6. (PDF) Opinion Mining and Sentiment Analysis Need Text Understanding

    opinion mining and sentiment analysis research papers

VIDEO

  1. 04 05 4 5 Opinion Mining and Sentiment Analysis Latent Aspect Rating Analysis Part 2 00 14 43

  2. Dr. Drone Prathap's 70,000 papers, maths ❌😱 but maths baralla 😂 #bharadwajavare #droneprathap

  3. Text mining in R and Twitter Sentiment Analytics

  4. Presentasi UAS Web Text Mining (Sentiment Analysis)

  5. 06 MIS 769 UNLV

  6. 04 02 4 2 Opinion Mining and Sentiment Analysis Sentiment Classification 00 11 47

COMMENTS

  1. Sentiment analysis and opinion mining on educational data: A survey

    Sentiment analysis, also known as opinion mining is a natural language processing technique (NLP) technique to identify the emotional tone behind a text (Bansal et al., 2022). The technique has been widely used to extract user opinions on products and services from their reviews and create actionable knowledge for an entity (Ligthart et al., 2021).

  2. [PDF] Opinion Mining and Sentiment Analysis

    Sentiment Analysis-An opinion mining tool C. Vanipriya T. Reddy R. Pallavi Computer Science International Journal Of Recent Advances in… 2020 TLDR The main purpose of the work described herein is to provide an efficient way of providing positive, negative and neutral review from the user's reviews about the product in lesser time. PDF

  3. Opinion Mining and Sentiment Analysis

    Opinion Mining and Sentiment Analysis is the first such comprehensive survey of this vibrant and important research area and will be of interest to anyone with an interest in opinion-oriented information-seeking systems. Article #: ISBN Information: Print ISBN: 9781601981509 Electronic ISBN: 9781601981516 INSPEC Accession Number:

  4. Opinion mining for national security: techniques, domain applications

    Opinion mining, or sentiment analysis, is a field in Natural Language Processing (NLP). It extracts people's thoughts, including assessments, attitudes, and emotions toward individuals, topics, and events. The task is technically challenging but incredibly useful. With the explosive growth of the digital platform in cyberspace, such as blogs and social networks, individuals and organisations ...

  5. Over a decade of social opinion mining: a systematic review

    This systematic review focuses on the evolving research area of Social Opinion Mining, tasked with the identification of multiple opinion dimensions, such as subjectivity, sentiment polarity, emotion, affect, sarcasm and irony, from user-generated content represented across multiple social media platforms and in various media formats, like text,...

  6. Opinion Mining and Sentiment Analysis

    In this paper, we consider opinion word extraction, one of the key problems in sentiment analysis. Sentiment analysis (or opinion mining) is an important research area within computational linguistics. Opinion words, which form an opinion lexicon, ...

  7. Analytical mapping of opinion mining and sentiment analysis research

    Opinion mining and sentiment analysis (OMSA) as a research discipline has emerged during last 15 years and provides a methodology to computationally process the unstructured data mainly to extract opinions and identify their sentiments. The relatively new but fast growing research discipline has changed a lot during these years. ... In fact now ...

  8. Opinion Mining and Sentiment Analysis: A Survey

    Opinion Mining and Sentiment Analysis: A Survey CC BY 4.0 Authors: Mohammad sadegh Hajmohammadi Universiti Teknologi Malaysia Roliana Ibrahim Universiti Teknologi Malaysia Zulaiha Ali Othman...

  9. A comprehensive bibliometric analysis on opinion mining and sentiment

    This study examines the global publication output on opinion mining and sentiment analysis from documents published in 2000 to 2020. Bibliometric indicators on the trends, most cited papers, authors, institutions, countries, funding agencies and research subject areas were independently screened and analysed using bibliometrix package in R.

  10. A survey on opinion mining and sentiment analysis: Tasks, approaches

    Pang and Lee [1] performed an extensive survey of more than three hundred papers by covering applications, common challenges for sentiment analysis, major tasks of opinion mining viz., opinion extraction, sentiment classification, polarity determination, and summarization.

  11. Sentiment Analysis and Opinion Mining

    Sentiment Analysis and Opinion Mining | SpringerLink Book © 2012 Sentiment Analysis and Opinion Mining Home Book Authors: Bing Liu Part of the book series: Synthesis Lectures on Human Language Technologies (SLHLT) 6028 Accesses 899 Citations Sections Table of contents About this book Authors and Affiliations About the author

  12. A survey on sentiment analysis methods, applications, and challenges

    Sentiment analysis is the process of gathering and analyzing people's opinions, thoughts, and impressions regarding various topics, products, subjects, and services. People's opinions can be beneficial to corporations, governments, and individuals for collecting information and making decisions based on opinion.

  13. Sentiment analysis and opinion mining on educational data: A survey

    Sentiment analysis AKA opinion mining is one of the most widely used NLP applications to identify human intentions from their reviews. In the education sector, opinion mining is used to listen to student opinions and enhance their learning-teaching practices pedagogically.

  14. A Review: Sentiment Analysis and Opinion Mining

    Abstract. The rapid growth in social media along its users has given rise to the need of Sentiment analysis also called Opinion mining or emotion abstraction, whose goal is to extract, determine, analyze and present the sentiments of the user and drawing a conclusion about the overall information they contain in less cost and efficient time complexity.

  15. Opinion mining and emotion recognition applied to ...

    This paper presents a comparison among several sentiment analysis classifiers using three different techniques - machine learning, deep learning, and an evolutionary approach called EvoMSA - for the classification of educational opinions in an Intelligent Learning Environment called ILE-Java. ... The blending of opinion mining and sentiment ...

  16. A Survey of Opinion Mining and Sentiment Analysis

    Automated opinion mining and summarization systems are thus needed, as subjective biases and mental limitations can be overcome with an objective sentiment analysis system. In the past decade, a considerable amount of research has been done in academia [58,76]. There are also numerous commercial companies that provide opinion mining services.

  17. PDF Opinion Mining and Sentiment Analysis: A Survey

    Abstract: Opinion Mining and Sentiment Analysis is the field of study that analyzes customer opinions, feedback, sentiments, evaluations, attitudes, and emotions from written language. It is one of the most active research areas in Natural Language Processing (NLP) and is also widely studied in data mining, Web mining, and text mining.

  18. (PDF) Sentiment analysis and opinion mining applied to scientific paper

    Sentiment analysis and opinion mining applied to scientific paper reviews Authors: Brian Keith Norambuena Universidad Católica del Norte (Chile) Exequiel Fuentes Lettura Claudio Meneses Villegas...

  19. [PDF] Opinion Mining and Sentiment Analysis

    A frame work for sentiment analysis with opinion mining for the case of hotel customer feedback is designed that automatically prepares a sentiment dataset for training and testing to extract unbiased opinions of hotel services from reviews to discover a suitable machine learning algorithm for the classification component of the framework. PDF.

  20. Sentiment analysis algorithms and applications: A survey

    Sentiment Analysis (SA) or Opinion Mining (OM) is the computational study of people's opinions, attitudes and emotions toward an entity. The entity can represent individuals, events or topics. These topics are most likely to be covered by reviews. The two expressions SA or OM are interchangeable. They express a mutual meaning.

  21. OPINION MINING AND SENTIMENT ANALYSIS Research Papers

    This paper reports a work in progress with contributions including: the development of a framework for gathering and analyzing the views and experiences of users of drug and cosmetic products using machine learning, text mining and sentiment analysis; the application of the proposed framework on Facebook comments and data from Twitter for brand ...

  22. Opinion Mining: What it is, Types & Techniques to Follow

    Opinion mining is a vital tool for businesses to extract valuable insights from public opinions. It helps in customer service, brand management, product development, and market research. The diverse types of opinion-mining techniques, from sentiment analysis to emotion analysis, provide complete insights for decision-making.

  23. A review on sentiment analysis and emotion detection from text

    This review paper provides understanding into levels of sentiment analysis, various emotion models, and the process of sentiment analysis and emotion detection from text. Finally, this paper discusses the challenges faced during sentiment and emotion analysis. Similar content being viewed by others

  24. The evolution of sentiment analysis—A review of research topics, venues

    Opinion mining and sentiment analysis are a welcomed topic for submission. 11.5% of the RANLP papers in 2015 was of sentiment analysis nature. Decision Support Systems is an Elsevier journal. The journal welcomes submissions that are relevant to theoretical and technical issues in the support of decision support systems foundations ...

  25. Journal of Medical Internet Research

    Correction: Public Opinion About COVID-19 on a Microblog Platform in China: Topic Modeling and Multidimensional Sentiment Analysis of Social Media J Med Internet Res 2024;26:e57233 doi: 10.2196/57233 Copy Citation to Clipboard