Metaheuristic and evolutionary methods for Feature Selection in Sentiment Analysis (a comparative study)

With the accelerated evolution of World Wide Web and the widespread of on-line collaborative tools, there is an increasing care towards automatic tools for Sentiment Analysis to provide a quantitative measure of "positivity" or "negativity" about opinions or social comments. But there are many challenges faced the sentiment analysis and evaluation process. These challenges become obstacles in analyzing the accurate meaning of sentiments and detecting the suitable sentiment polarity. The most important challenge is to identify and extract features we will use in our model. In this paper, we hand over an overview of the last spread out techniques for features selection in sentiment analysis based on meta heuristics and evolutionary algorithms as a quick reference guide in the choice of the most suitable methods for solving a specific problem in the sentiment analysis field more precisely in the feature selection stage.