Sentiment classification of reviews using combination of Firefly Algorithm and ANN

With the availability of many social media sites, the reviews and comments by the customers are freely available for analysis. Most of these reviews are textual as per the content matter.Thus, proper processing need to be done for future use of the reviews. As reviews are in text, the amount of words need to be processed for any analysis work is very large in amount. So, an approach needs to be adopted to minimize the amount of word without affecting the result of the analysis. Thus, in this paper the Firefly algorithm is used to select the words / features that can act as a representative of the whole set of words. The output of Firefly algorithm i.e., selected features act as input of ANN. In this paper, a hybridization of Firefly algorithm and ANN is carried out for better accuracy result. The result of the proposed approach is analyzed by using confusion matrix and various evaluation parameters.