Product Review-Based Customer Sentiment Analysis Using an Ensemble of mRMR and Forest Optimization Algorithm (FOA)

This research presents a way of feature selection problem for classification sentiments that use ensemble-based classifier. includes hybrid approach minimum redundancy and maximum relevance (mRMR) technique Forest Optimization Algorithm (FOA) (i.e. mRMR-FOA) based selection. Before applying the FOA on sentiment analysis, it has been used as applied 10 different datasets publically available UCI machine learning repository. The classifiers example k-Nearest Neighbor (k-NN), Support Vector Machine (SVM) Naïve Bayes ensemble algorithm datasets. mRMR-FOA uses Blitzer’s dataset (customer reviews electronic products survey) to select significant features. noticed improve by 12 18%. evaluated results are further enhanced k-NN, NB SVM with an accuracy 88.47% analysis task.