A proposal for creating a Chinese emotion thesaurus with tag of emotion intensity

In recent years, researchers have begun to pay more attention to the emotion recognition in natural language processing. In order to help this pursuit, this paper proposes a semi-automatic approach to create a Chinese emotion thesaurus with tag of emotion intensity based on two kinds of language resources HowNet and Tongyici Cilin. As a basic emotion resource, the emotion thesaurus should be used to help the classification and recognition of emotion in Chinese. We present a new algorithm of the semantic similarity computation for aiding the emotion intensity computation between words. The experimental results on verbs prove that our approach is feasible and effective.