What question did this study set out to answer?

This research aims to develop a model for analyzing sentiment in movie reviews using advanced techniques in machine learning and natural language processing.

June 30, 2015Open Access

Feature Selection and Classification Approach for Sentiment Analysis

Key Points

This research aims to develop a model for analyzing sentiment in movie reviews using advanced techniques in machine learning and natural language processing.
Employed data pre-processing on movie review datasets.
Investigated performance of Naive Bayes and SVM classifiers with various feature selection schemes.
Extended sentiment analysis model to evaluate higher order n-grams.
Demonstrated that certain feature selection schemes significantly improved classification accuracy.
Found Naive Bayes and SVM classifiers performed variably based on feature selection strategies.

Abstract

Sentiment analysis and Opinion mining has emerged as a popular and efficient technique for information retrieval and web data analysis. The exponential growth of the user generated content has opened new horizons for research in the field of sentiment analysis. This paper proposes a model for sentiment analysis of movie reviews using a combination of natural language processing and machine learning approaches. Firstly, different data pre-processing schemes are applied on the dataset. Secondly, the behaviour of two classifiers, Naive Bayes and SVM, is investigated in combination with different feature selection schemes to obtain the results for sentiment analysis. Thirdly, the proposed model for sentiment analysis is extended to obtain the results for higher order n-grams.

Bookmark

View Full Paper