Method for Computing Emotions of Tweets with an Emoticon

Abstract

In text-based message exchange services, non-verbal expressions, such as emoticons, are typically used. However, their usage is intuitive, and many questions persist as to how emoticons affect the emotional aspect of messages. Therefore, we formulate the effect of emoticons on emotions of tweets with an emoticon and propose a method for computing emotion values of tweets with an emoticon. Initially, emotion values of emoticons and those of tweets with an emoticon are determined based on results of questionnaires. Subsequently, emotion values of tweets are calculated via two sentiment analysis tools. We then apply multiple regression analysis to the three types of emotion values, and thus we obtain multiple regression equations to compute emotion values of tweets with an emoticon. Our performance evaluation indicates that the proposed method is effective in terms of computing values of the following nine emotions: "Sorrow," "Disgust," "Relief," "Fear," "Liking," "Joy," "Surprise," "Anger," and "Shame."