Article: Capturing user sentiments for online Indian movie reviews: A comparative analysis of different machine-learning models
Journal: The Electronic Library. [B class as per ABDC list, Scopus Indexed, Impact factor - 0.484]
Purpose: Sentiment analysis and opinion mining are emerging areas of research for analyzing Web data and capturing users’ sentiments. This research presents sentiment analysis of an Indian movie-review corpus using natural language processing and various machine-learning classifiers. Design/methodology/approach: In this paper, a comparative study between three machine-learning classifiers (Bayesian, naïve Bayesian and support vector machine (SVM) was performed. All the classifiers were trained on the words/features of the corpus extracted, using five different feature-selection algorithms (chi-square, info-gain, gain-ratio, one-R, and relief-F attributes), and a comparative study was performed between them. The classifiers and feature-selection approaches were evaluated using different metrics (F-value, false-positive rate (FP rate), and training time). Findings: The results of this study show that, for the maximum number of features, the relief-F feature-selection approach was found to be the best, with better F-values, a low FP rate, and less time needed to train the classifiers while, for the least number of features, one-R was better than relief-F. When the evaluation was performed for machine-learning classifiers, SVM was found to be superior, although the Bayesian classifier was comparable with SVM. Keywords: Sentiments Analysis, Opinion Mining, Machine Learning Classifiers, Indian Movie Review.