A survey of sentiment analysis in social media

• Published in: Knowledge and information systems 2019-08, Vol.60 (2), p.617-663
• Main Authors: Yue, Lin, Chen, Weitong, Li, Xue, Zuo, Wanli, Yin, Minghao
• Format: Article
• Language: English
• Subjects: Computer Science; Data mining; Data Mining and Knowledge Discovery; Database Management; Digital media; Information Storage and Retrieval; Information Systems and Communication Service; Information Systems Applications (incl.Internet); IT in Business; Sentiment analysis; Social networks; Survey Paper
• ISSN: 0219-1377; 0219-3116
• DOI: 10.1007/s10115-018-1236-4

Sentiments or opinions from social media provide the most up-to-date and inclusive information, due to the proliferation of social media and the low barrier for posting the message. Despite the growing importance of sentiment analysis, this area lacks a concise and systematic arrangement of prior efforts. It is essential to: (1) analyze its progress over the years, (2) provide an overview of the main advances achieved so far, and (3) outline remaining limitations. Several essential aspects, therefore, are addressed within the scope of this survey. On the one hand, this paper focuses on presenting typical methods from three different perspectives (task-oriented, granularity-oriented, methodology-oriented) in the area of sentiment analysis. Specifically, a large quantity of techniques and methods are categorized and compared. On the other hand, different types of data and advanced tools for research are introduced, as well as their limitations. On the basis of these materials, the essential prospects lying ahead for sentiment analysis are identified and discussed.