SVM-Based Comments Classification and Mining of Virtual Community: For Case of Sentiment Classification of Hotel Reviews

Comments of virtual communities are very import to the operation and development of an enterprise, through analysis the sentiment of the comments, we can mine the user's semantic orientation and preferences or hates, it is very helpful for enterprises to improve their products and services and for individuals to use these information rationally. This paper takes hotel review of the virtual community for example, to use key technologies of support vector machine (SVM) and sentiment classification to build a small domain sentiment corpus, and to propose a sentiment classification model based on the corpus to reach the purpose of feature dimension reduction. We choose a hotel reviews corpus as instance to validate the method we proposed in this paper, the results of the experiment shows that the accuracy of support vector machine algorithm has been enhanced by adding a user's sentiment corpus. This method can be fatherly extended to apply to other comments of the virtual communities.