Tibetan Text Sentiment Classification Based on Rules

We consider the problem of Tibetan text sentiment analysis by referencing the method based on emotion dictionary of Chinese and English. The method we proposed divided Tibetan into three categories including positive, negative and neutral. We took polarity phrase, which is consists of polarity words and qualifiers as the basic unit of polarity calculation. We also studied the influence of sentence emotion polarity caused by turning words and proposed a Tibetan text sentiment analysis method based on polar dictionary. Experimental results show that the method we proposed get a good result.