Emotion analysis: A survey

Abstract

Emotions form a very important and basic aspect of our lives. Whatever we do, whatever we say, somehow does reflect some of our emotions, though may not be directly. To understand the very fundamental behavior of a human, we need to analyze these emotions through some emotional data, also called, the affect data. This data can be text, voice, facial expressions etc. Using this emotional data for analyzing the emotions also forms an interdisciplinary field, called Affective Computing. Computation of emotions is a very challenging task, much work has been done but many more increments are also possible. With the advent of social networking sites, many people tend to get attracted towards analyzing this very text available on these various sites. Analyzing this data over the Internet means we are spanning across the whole continent, going through all the cultures and communities across. This paper summarizes the previous works done in the field of textual emotion analysis based on various emotional models and computational approaches used.