Analysis of Chinese Comments on Douban Based on Naive Bayes

The naive Bayesian classification is commonly used as a basic machine learning classification. In this paper, we use the sentimental classifier based on naive Bayesian principle for Chinese text sentimental classification. The training set and test set of this article are both from the Chinese film reviews in Douban and crawled by python. Based on naive Bayesian principle, we construct a data sentiment classifier. And analyze the emotional inclination of the test text using the constructed sentimental classifier. And compared with the classification result of the classifier based on TF-IDF and the classification result of the sentimental naive Bayesian classifier which based on the traditional Chinese sentiment dictionary. To test the influence of the naive Bayesian classification and the composition of the training set on the Chinese text sentiment classification. The experimental results show that the naive Bayesian sentiment classifier based on the training set of the same data source can classify Chinese text in the uniform field efficiently and accurately.