Affective Computing and Sentiment Analysis

Cambria, Erik; Das, Dipankar; Bandyopadhyay, Sivaji; Feraco, Antonio

doi:10.1007/978-3-319-55394-8_1

Cited by 196 publications

(91 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…‘Sentic computing’ [30,31] is a multi-disciplinary approach to NLP and understanding at the crossroads between affective computing, information extraction, and common-sense reasoning and exploits both computer and human sciences to better interpret and process social information on the Web. In sentic computing, the analysis of natural language is based on common-sense reasoning tools which enable the analysis of text not only at the document, page or paragraph level but also at the sentence, clause and concept level [32]. Sentiment analysis requires tackling many ‘NLP’ sub-tasks [33,34]; this is the reason for high usage of ‘NLP’ by him.…”

Section: Resultsmentioning

confidence: 99%

Bibliometrics of sentiment analysis literature

Keramatfar

Amirkhani

2018

Journal of Information Science

View full text Add to dashboard Cite

This article provides a bibliometric study of the sentiment analysis literature based on Web of Science (WoS) until the end of 2016 to evaluate current research trends, quantitatively and qualitatively. We concentrate on the analysis of scientific documents, distribution of subject categories, languages of documents and languages that have been more investigated in sentiment analysis, most prolific and impactful authors and institutions, venues of publications and their geographic distribution, most cited and hot documents, trends of keywords and future works. Our investigations demonstrate that the most frequent subject categories in this field are computer science, engineering, telecommunications, linguistics, operations research and management science, information science and library science, business and economics, automation and control systems, robotics and social sciences. In addition, the most active venue of publication in this field is Lecture Notes in Computer Science ( LNCS). The United States, China and Singapore have the most prolific or impactful institutions. A keyword analysis demonstrates that sentiment analysis is a more accepted term than opinion mining. Twitter is the most used social network for sentiment analysis and Support Vector Machine ( SVM) is the most used classification method. We also present the most cited and hot documents in this field and authors’ suggestions for future works.

show abstract

Section: Resultsmentioning

confidence: 99%

Bibliometrics of sentiment analysis literature

Keramatfar

Amirkhani

2018

Journal of Information Science

View full text Add to dashboard Cite

show abstract

“…Many researchers have proposed more fine-grained models. Burns et al proposed a two-fold LDA model to identify both aspects and positive or negative sentiments in review sentences [8]. One LDA runs for aspect extraction while another LDA runs for sentiment identification.…”

Section: Related Workmentioning

confidence: 99%

“…Probabilistic topic models, which are typically built on a basic latent Dirichlet allocation (LDA) model [1], have been used for aspect-based sentiment analysis [2][3][4][5][6][7][8], where the semantic aspect can be naturally formulated as one type of latent topic. Much work has extended the traditional topic model from the document level to the sentence level and, in so doing, has extracted more detailed information from reviews.…”

Section: Introductionmentioning

confidence: 99%

Mining Review Unit Model for Online Review Analysis

Peng

You

et al. 2020

IEEE Access

View full text Add to dashboard Cite

An increasing number of people are choosing to shop online; hence, online reviews are an increasingly influential factor in consumer purchasing decisions. However, extracting useful information from online reviews is a challenge in the analysis of consumer sentiment. In this paper, we focus on the automatic discovery of the features evaluated in online reviews and the expression of sentiment. We propose a novel fine-grained topic model called the "review unit topic model" (RUTM) to extract semantic meanings and polarities. In this model, a review unit rather than a review sentence is treated as the representational model, and prior knowledge of sentiment is further exploited to identify aspect-aware sentiment polarities. We evaluate RUTM extensively using real-world review data. Experimental results demonstrate that the proposed model outperforms well-established baseline models in sentiment analysis tasks.

show abstract

“…For example, the use of OntoSenticNet [35] has been successful in supporting a semantic representation of opinions through the developed commonsense ontology. In fact, sentiment analysis is considered as a typical ‘suitcase problem’ [36,37]. This task is made even harder when it comes to addressing the ambiguity and shortness of posts, such as tweets, in unstructured social data content.…”

Section: Related Workmentioning

confidence: 99%

CredSaT: Credibility ranking of users in big social data incorporating semantic analysis and temporal factor

Abu-Salih

Wongthongtham

Chan

et al. 2018

Journal of Information Science

View full text Add to dashboard Cite

The widespread use of big social data has pointed the research community in several significant directions. In particular, the notion of social trust has attracted a great deal of attention from information processors / computer scientists and information consumers / formal organizations. This is evident in various applications such as recommendation systems, viral marketing and expertise retrieval. Hence, it is essential to have frameworks that can temporally measure users' credibility in all domains categorised under big social data. This paper presents CredSaT (Credibility incorporating Semantic analysis and Temporal factor): a fine-grained users' credibility analysis framework for big social data. A novel metric that includes both new and current features, as well as the temporal factor, is harnessed to establish the credibility ranking of users. Experiments on real-world dataset demonstrate the effectiveness and applicability of our model to indicate highly domain-based trustworthy users. Further, CredSaT shows the capacity in capturing spammers and other anomalous users.

show abstract

Affective Computing and Sentiment Analysis

Cited by 196 publications

References 36 publications

Bibliometrics of sentiment analysis literature

Bibliometrics of sentiment analysis literature

Mining Review Unit Model for Online Review Analysis

CredSaT: Credibility ranking of users in big social data incorporating semantic analysis and temporal factor

Contact Info

Product

Resources

About