Building a Chinese Slang Sentiment Lexicon Using Online Crowdsourcing Dictionaries

Abstract

Microblogging platforms are now one of the most popular means of social media in China. Carrying sentiment analysis on those platforms can provide valuable insights for various uses. However, the heavy use of Internet slang in microblog contexts and the lack of slang vocabulary in sentiment lexicons make it problematic. Aimed at this issue, we propose a method to build a comprehensive sentiment lexicon for Chinese internet slang. We leverage online sources to acquire a list of slang words first. Then, a method based on SO-PMI (Semantic Orientation from Pointwise Mutual Information) is used to assign the sentiment polarity to each word. By Utilizing online sources, the slang lexicon has comprehensive coverage of internet slang. The sentiment categorization method based on SO-PMI guarantees the sentiment polarity we acquire from microblog flatforms is compatible with the same microblog context the lexicon aimed to analyze.