Chinese microblogging emotion classification based on support vector machine

Through the analysis and study of the emotional characteristics in Chinese micro-blog, this paper proposed a multidimensional sentiment classification method based micro-blog emotion classification, emoticon in micro-blog is adopted to train the support vector machine and divide micro-blog into seven types of emotions: happiness, fondness, sorrow, anger, fear, detestation and surprise. We used micro-blog emoticon to initial screen large-scale unmarked data, and automatically labeled them into seven types, then used this emotional corpus as training set to train the emotion classifier to classify micro-blog data into multiple emotion categories. The experimental results show that precision of unigram model for each type can reach 63.7%. Meanwhile, different feature selection methods for support vector machines and Naive Bayes classifier experiment have been adopted in the experiment, the precision and recall has reached more than 71%.