Title: Product opinion analysis using text mining and analysis

Authors: K. Marimuthu; Anuj Shankar; Rashmi Ranganathan; R. Niranchana

Addresses: School of Computer Science and Engineering, VIT University, Vellore-632 014, Tamilnadu, India ' School of Computer Science and Engineering, VIT University, Vellore-632 014, Tamilnadu, India ' School of Computer Science and Engineering, VIT University, Vellore-632 014, Tamilnadu, India ' School of Computer Science and Engineering, VIT University, Vellore-632 014, Tamilnadu, India

Abstract: The enormous growth and usage of e-commerce offer positive ways to any business by sharing the emotions, feelings and experiences. Web users are benefited with valuable online reviews. There are many instances, where these reviews are not considered for evaluation of a product in the market, thus affecting the sales of the products. We intend to solve the problem of sentiment polarity computation, which is one of the most basic problems of sentiment analysis. A general process for sentiment polarity computation, department wise classification and feature extraction is proposed with detailed procedure. Data on online product reviews from Amazon.com was used in this study. ProSent is a real-time web service, which provides insights of the product by applying sentiment analysis on the reviews. It eases the way to manage bulk customer reviews and also simplifies handling of customer reviews with customisable workflow processes and meaningful graphs and charts.

Keywords: review analysis; user registration; dashboard; NLP; overview of product; text mining.

DOI: 10.1504/IJSGGC.2018.091351

International Journal of Smart Grid and Green Communications, 2018 Vol.1 No.3, pp.227 - 234

Received: 13 May 2017
Accepted: 22 May 2017
Published online: 27 Apr 2018 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article