Firefly with Levy Based Feature Selection with Multilayer Perceptron for Sentiment Analysis

Abstract

—Sentimental Analysis (SA) has recently received a lot of attention in decision-making because it can extract and analyze sentiments from web-based reviews made by customers. In this case, SA has been used as a Sentiment Classification (SC) problem, in which reviews are typically labeled as positive or negative depending upon online reviews. By combining FS (Feature Selection) and categorization, this work proposes an effective SA method for internet reviews. FireFly (FF) and Levy Flights (FFL) algorithms have been used for extracting features of web-based reviews, and also the Multilayer Perceptron (MLP) framework has been used to categorize the emotions. A standard DVD database displayed the efficacy of the FF-MLP model on the testing. The outcome shows that the suggested FF-MLP system accomplishes enhanced performance with maximum sensitivity of 98.97%, specificity of 93.67%, accuracy of 97.97%, F-score of 98.75, and kappa of 93.32%.