The evolution of sentiment analysis—A review of research topics, venues, and top cited papers

A computer-assisted literature review, where the roots of sentiment analysis are in the studies on public opinion analysis at the beginning of 20th century and in the text subjectivity analysis performed by the computational linguistics community in 1990's, and the top-20 cited papers from Google Scholar and Scopus are presented.

Abstract

Sentiment analysis is one of the fastest growing research areas in computer\nscience, making it challenging to keep track of all the activities in the area.\nWe present a computer-assisted literature review, where we utilize both text\nmining and qualitative coding, and analyze 6,996 papers from Scopus. We find\nthat the roots of sentiment analysis are in the studies on public opinion\nanalysis at the beginning of 20th century and in the text subjectivity analysis\nperformed by the computational linguistics community in 1990's. However, the\noutbreak of computer-based sentiment analysis only occurred with the\navailability of subjective texts on the Web. Consequently, 99% of the papers\nhave been published after 2004. Sentiment analysis papers are scattered to\nmultiple publication venues, and the combined number of papers in the top-15\nvenues only represent ca. 30% of the papers in total. We present the top-20\ncited papers from Google Scholar and Scopus and a taxonomy of research topics.\nIn recent years, sentiment analysis has shifted from analyzing online product\nreviews to social media texts from Twitter and Facebook. Many topics beyond\nproduct reviews like stock markets, elections, disasters, medicine, software\nengineering and cyberbullying extend the utilization of sentiment analysis\n