Sentiment classification of Chinese traveler reviews by support vector machine algorithm

Nowadays, online word-of-mouth has turned to be a very important resource for electronic businesses. How to analyze user generated reviews and to classify them into different sentiment classes is gradually becoming a question that people pay close attention to. In this field, special challenges are associated with the mining of traveler reviews. At present, there is some research on sentiment analysis for English traveler generated reviews, but very few studies pay attention to sentiment analysis for traveler reviews in Chinese. China is the largest country in terms of the number of Internet users. Internet technologies are gradually playing more and more important roles for many industries including tourism industry. The lack of sentiment analysis methods will block the use of word-of-mouth for tourism industry in China. To solve the problem, this study conducts an exploring research on sentiment analysis to Chinese traveler reviews by support vector machine (SVM) algorithm. The experiment data of Chinese reviews for hotels are downloaded from www.ctrip.com, the largest online travel agency in China. Empirical results indicate that, comparing to prior studies on English reviews, SVM algorithm can gain a very well performance of sentiment classification for traveler reviews in Chinese.