Sentiment Classification of Documents Based on Latent Semantic Analysis

Abstract

Sentiment classification has attracted increasing interest from natural language processing. The goal of sentiment classification is to automatically identify whether a given piece of text expresses positive or negative opinion on a topic of interest. Latent semantic analysis (LSA) has been shown to be extremely useful in information retrieval. In this paper, we propose a new method, based on LSA and support vector machine (SVM) to improve the sentiment classification performance. This method takes the advantage of both LSA and SVM. During the training process, SVM makes use of its excellent classification ability to conduct the sentiment classification first. To show that our method is feasible and effective, we designed two experiments and the experimental result shows that the introduction of SVM outperforms the other experiment in precision of the polarity analysis.