A review of emotion sensing: categorization models and algorithms
- PDF / 1,351,888 Bytes
- 30 Pages / 439.37 x 666.142 pts Page_size
- 77 Downloads / 182 Views
A review of emotion sensing: categorization models and algorithms Zhaoxia Wang 1 & Seng-Beng Ho 2 & Erik Cambria 3 Received: 4 January 2019 / Revised: 10 July 2019 / Accepted: 1 October 2019 # Springer Science+Business Media, LLC, part of Springer Nature 2019
Abstract
Sentiment analysis consists in the identification of the sentiment polarity associated with a target object, such as a book, a movie or a phone. Sentiments reflect feelings and attitudes, while emotions provide a finer characterization of the sentiments involved. With the huge number of comments generated daily on the Internet, besides sentiment analysis, emotion identification has drawn keen interest from different researchers, businessmen and politicians for polling public opinions and attitudes. This paper reviews and discusses existing emotion categorization models for emotion analysis and proposes methods that enhance existing emotion research. We carried out emotion analysis by inviting experts from different research areas to produce comprehensive results. Moreover, a computational emotion sensing model is proposed, and future improvements are discussed in this paper. Keywords Affective computing . Emotion definition . Emotion categorization model . Sentiment analysis
* Erik Cambria [email protected] Zhaoxia Wang [email protected] Seng-Beng Ho [email protected]
1
School of Information Systems, Singapore Management University, 80 Stamford Rd, Singapore 178902, Singapore
2
Institute of High Performance Computing, A*STAR, 1 Fusionopolis Way, Singapore 138632, Singapore
3
School of Computer Science and Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore 639798, Singapore
Multimedia Tools and Applications
1 Introduction With the advent of Web 2.0, an increasing number of users is willing to share their comments or experiences on social media [1]. This provides significant opportunities for those who are eager to gauge public opinion or consumer’s attitudes toward their services, products or other issues they care about. Sentiment analysis is a research area that aims to detect sentiment polarity from text, audio or video [2]. Sentiment polarity can be positive, such as ‘What a nice game this phone has! I enjoy it so much!’; negative, such as ‘I am feeling blue about this brand, angry about it since it cannot power on again’; neutral, such as ‘There is an iPhoneX on his table’; and mixed or ambivalent, such as ‘I feel not well and very tired today, but I am very happy about the new results’. Compared to sentiment analysis, emotion sensing yields emotion identification results [3, 4]. It drills deeper to reveal the exact emotions in negative or positive sentiments and recognizes the exact emotions expressed within text. For example, the above text ‘I am feeling blue about this brand, angry about it since it cannot power on again’ not only expresses a negative sentiment, it also expresses the “anger” emotion towards “this brand”. Nowadays, emotion sensing has attracted not only increasing interest from researc
Data Loading...
