Beyond Sentiment Analysis: A Review of Recent Trends in Text Based Sentiment Analysis and Emotion Detection

Sentiment Analysis is probably one of the best-known area in text mining. However, in recent years, as big data rose in popularity more areas of text classification are being explored. Perhaps the next task to catch on is emotion detection, the task of identifying emotions. This is because emotions are the finer grained information which could be extracted from opinions. So besides writer sentiments, writer emotion is also a valuable data. Emotion detection can be done using text, facial expressions, verbal communications and brain waves; however, the focus of this review is on text-based sentiment analysis and emotion detection. The internet has provided an avenue for the public to express their opinions easily. These expressions not only contain positive or negative sentiments, it contains emotions as well. These emotions can help in social behaviour analysis, decision and policy makings for companies and the country. Emotion detection can further support other tasks such as opinion mining and early depression detection. This review provides the challenges in these tasks. We summarize some of methods they used. We also look at the models of emotion classes that are generally referenced. The trend of text-based emotion detection has shifted from the flexibility to the task and better performance.

Automated summary

Sentiment Analysis is a well-known area in text mining, but recently more areas of text classification, such as emotion detection, are being explored. Emotion detection is valuable for social behavior analysis and decision making. It can support tasks such as opinion mining and early depression detection. This review focuses on text-based sentiment analysis and emotion detection, summarizing methods and examining models of emotion classes.