State Grid Qingdao Power Supply Company

Abstract—We propose to simultaneously identify opinion targets and opinion-bearing words based on multi-features in Chinese micro-blog post, and decompose our task into three phases: (1) construct opinion-bearing words dictionary and identify opinion-bearing word in a sentence from Chinese micro-blog; (2) design multiple features related to opinion target identification, containing Token, POS, WD, DDR; (3) design three kinds of different feature templates to identify feature-opinion pairs <opinion target, opinion-bearing word> in Chinese micro-blog post. The experiments show that our approach is very effective and get better performance than the baselines. Keywords—Opinion mining, micro-blog, sentiment polarity, sentiment analysis I