Comparison of emotion lexicons

Although the research of emotion detection from social media grows, not much research has been focused on the construction of emotion lexicon, which plays an important role on emotion classification. In this paper, we compare frequently used emotion lexicons EmoSenticNet (ESN), and National Research Council Canada (NRC) as well as relatively newer emotion lexicons DepecheMood (DPM), and Topic based DepecheMood (TDPM). Comparisons are performed in terms of size, type and kind of words used to construct lexicons. The lexicons, and some of their subset combinations, are evaluated via emotion classification process on Semeval-2007 test dataset. Experiments provide detailed comparison of the effects of lexicons on emotion classification process.