Imbalanced Learning Based Sentiment Classification of Stock Reviews

The stock reviews are important professional advice for stock traders. Based on the massive stock reviews available online, an automatic approach which can identify the emotional tendency hidden in stock reviews will provide tremendous help to stock traders. A sentiment classification strategy is proposed for stock reviews analysis. Firstly, stock reviews are collected from the Internet and construct a labeled corpus. Secondly, a feature extraction approach is designed which can effectively map the corpus into a structured matrix. Finally, four classifiers are evaluated on multiple criteria. The synthetic oversampling approach is utilized to overcome the imbalanced distribution of positive and negative reviews. The experimental results demonstrate that the SVM algorithms coupled with SMOTE can achieve the highest performance for sentiment classification on the real world Chinese stock review corpus.