A Review of Different Approaches for Detecting Emotion from Text

Abstract

Emotion detection and analysis is one of the challenging and emerging issues in the field of natural language processing (NLP). Detecting an individual’s emotional state from textual data is an active area of study, along with identifying emotions from facial and audio records. The study of emotions can benefit from many applications in various fields, including neuroscience, data mining, psychology, human-computer interaction, e-learning, information filtering systems and cognitive science. The rich source of text available in the Social media, blogs, customer review, news articles can be a useful resource to explore various insights in text mining, including emotions. The purpose of this study is to provide a survey of existing approaches, models, datasets, lexicons, metrics and their limitations in the detection of emotions from the text useful for researchers in carrying out emotion detection activities.