Lexicon Based and Multi-Criteria Decision Making (MCDM) Approach for Detecting Emotions from Arabic Microblog Text

Emotions serve as a communicative function both within the brain and within the social group. Most of previous opinion mining studies applied on Arabic microblog text to identify positive, negative or neutral polarity. This paper studies the problem of detecting multiple emotion classes in Arabic microblog text (e.g. Twitter). Incoming Arabic microblog text is classified into one of fine grained emotional classes {happiness, sadness, fear, anger, disgust or none} if exists or mixed emotion if text contains multiple emotions e.g. {Happiness/Fear} or {Anger/Disgust}. We applied a combined approach of lexicon approach and Multi-Criteria Decision Making approach. We use a conditioned plot to classify and analyze the text by generating a two dimensional graphic analysis space, one dimension represents observations (tweets) and the other represents our variables (5 emotional scores). The experimental results show that our proposed approach by using the conditioned plot able to classify text into different fine grained emotions, and also able to classify Arabic text with mixed emotions.