Conflicting views analysis algorithms

With the rapid development and popularity of the Internet technology, more and more people like to share their feelings and experiences on the Internet. The increasing rich in network resources, such as personal blogs, online reviews, etc., provide us with new opportunities and challenges. Opinion mining is talking about how to use information technology to mining, and understand the views of others. In this paper, the main work is to give the data set a label, then get it into the vector space model, let the text data digitization, use support vector machine (SVM), Naive Bayes and decision tree classifier. The purpose is to identify the comments that include conflicting views and their overall tendency of emotion. The experimental results show that the proposed method has a certain effect.