Sentiment Analysis Based Product Selection for Enhancing E-Commerce
P. Sudhakaran1, M. Jaiganesh2
1Dr. P. Sudhakaran, Professor, Department of CSE, SRM TRP Engineering College, Trichy (Tamil Nadu), India.
2M. Jaiganesh, Assistant Professor, Department of CSE, SRM TRP Engineering College, Trichy (Tamil Nadu), India.
Manuscript received on 12 January 2020 | Revised Manuscript received on 08 February 2020 | Manuscript Published on 20 February 2020 | PP: 389-394 | Volume-9 Issue-3S January 2020 | Retrieval Number: C10830193S20/2020©BEIESP | DOI: 10.35940/ijitee.C1083.0193S20
Open Access | Editorial and Publishing Policies | Cite | Zenodo | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: One of the fast growing, developing and highly used technology in various computing industries is data mining. Sentiment or opinion mining is a kind of data mining, where it follows the major processes of natural language processing. Nowadays, sentiment analysis meets a high demand. In this paper, it is aimed to consider the problems of sentiment analysis such as classification on opinion and attribute words, because it is the basic problem of sentiment analysis. This paper aimed to use one of the popular machine learning algorithms as Multi-Class Support Machine algorithm for classifying sentiment polarity with detailed description. The proposed method is implemented in Python software and experimented on onlineproduct-reviews data taken from Amazon.com. Sentence level and opinion level classification is obtained with promised outcomes. From the results it is noted that the proposed method outperforms than the existing method such as Naïve Bayes and Random Forest algorithms.
Keywords: Sentiment Analysis, Opinion Mining, E-Commerce, Polarity Classification, Machine Learning Algorithms, Customer Review Data, Amazon Data.
Scope of the Article: Software Product Lines