A Weighted Genetic Approach for Feature Selection in Sentiment Analysis

Abstract

The Sentiment Analysis has been witnessing a booming interest in recent years, due to the enormous growth of digital content, and various types of online reviews such as product and movie reviews. The aim of Sentiment Analysis is to use automated tools to detect and classify subjective information from these reviews. Feature selection happens to be an important step to extract and select more efficient text features, and at the same time to try improve the performance of the used classifier for Opinion Classification task. This paper proposes a methodology based on Genetic Algorithms to optimize the feature selection process for polarity classification. First, it uses a supervised weighting method in order to prune the searching space then, this weighting method is combined with stochastic search methods that generate the next feature subset in a heuristic manner. In order to validate the proposed method, we compared it with three feature selection methods on different sizes of feature subsets. The experimental results show the efficiency of our proposed method.