An Optimal Feature Selection with Ensemble Based Classification of Sentiments Using Forest Optimization Algorithm for Product Review
R. Sathya, L. R. Aravind Babu · Zenodo (CERN European Organization for Nuclear Research) · 2021
Feature subset selection is a method to select a set of relevant features from a high dimensionality dataset to optimize the performance of classifiers. The meaningful words extracted from data, forms a set of features for Sentiment Analysis (SA). The various evolutionary algorithms, like Particle Swarm Optimization (PSO) and Genetic Algorithm (GA), have been applied to subset for feature selection problem and computational can still be improved. This paper presents a result to feature subset selection problem for classification of Sentiment Analysis by means of ensemble-based classifiers. It involves of a hybrid technique of Forest Optimization Algorithm (FOA) and Maximum Relevance and minimum redundancy and (MRmr) based feature selection. Ensemble-based classification is implemented to improve the results of individual classifiers. The Forest Optimization Algorithm as a feature selection technique has been applied to many classification datasets. The classifiers used for ensemble methods for are the Naïve Bayes (NB) and k-Nearest Neighbor (k-NN). The outcomes are further enhanced by ensemble of k-NN, NB, and Support Vector Machine (SVM) with more accuracy.