Sentiment Reviews Classification using Hybrid Feature Selection

Abstract

In recent years there has been a steady increase in interest from brands, companies and researchers in Sentiment Analysis and its application to business analytics. It is the process of determining the emotional tone behind a series of words, used to gain an understanding of the attitudes, opinions and emotions expressed within an online mention. Sentiment analysis is a feature of text analysis and natural language processing (NLP) research that is increasingly growing in popularity as a multitude of use-cases emerges. Lexicon based and Machine learning is the two methods used for analysis the sentiments from the content. The proposed feature selection model Ssentiment Reviews Classification using Hybrid Feature Selection (SRCHFS) that extract synsets feature set coupled with Correlation feature selection method can improve the performance of sentiment classification. Nouns, verbs, adjectives and adverbs are organized into synsets, each representing one underlying lexical concept. A set of cognitive synsets is selected using WordNet based POS (Part Of Speech). Support Vector Machine (SVM) classifier is used for sentiment classification on a data set of Movie reviews, Multi Domain product reviews, Amazon Cell phone reviews and Yelp Restaurant reviews. The experimental outcome might result into better accuracy with the existing studies.