An automatic classification system for the stock comments

Abstract

The online stock comments are known to have some impacts on the trend of the stock market. In this paper, we design and implement an automatic classification system for the stock comments, which is an important issue in discussing the relation between the trend of the stock market and the stock comments. A classifier based on support vector machine (SVM) is established in which the topic words are considered as the features of the classification for the stock comments. The number of the topic words is only a few dozen because the topic words are only related to the online stock comments. Therefore, our system does not suffer from the curse of dimensionality which is a challenge in the common text classification. The experiment results on some datasets of the stock comments show our method is effective and can be regarded as an automatic tool for the classification of the stock comments.