Application of Chinese sentiment categorization to digital products reviews

Abstract

Sentiment categorization have been widely explored in many fields, such as government policy, information monitoring, product tracking, etc. This paper adopts k-NN, Naive Bayes and SVM classifiers to categorize sentiments contained in on-line Chinese reviews on digital products. Our experimental results show that combining the words and phrases with sentiment orientation as hybrid features, SWM classifier achieves an accuracy of 96,47%, which is words of all parts of speech as features.