Authors: Gaurav Kumar; N. Parimala
Addresses: School of Computer and Systems Sciences, Jawaharlal Nehru University, New Delhi, India ' School of Computer and Systems Sciences, Jawaharlal Nehru University, New Delhi, India
Abstract: In recent times, reviews of products by customers have been proliferating on the online platform. Majority of the reviews are lengthy, and going through the reviews before making a decision can be a tedious task for the user. In this paper, we extract the popular features from customers' reviews to analyse the possible opinions of these features. Choosing a product from the different combination of opinions for these features is treated as a multi-criteria decision making (MCDM) problem. Weighted sum method, a MCDM approach, is used to evaluate the priority score for each product. The product with the highest score is recommended to the user. Real-time dataset from Amazon is used to evaluate our system's performance. The experimental result shows that our proposed method produces a promising result which can help the user in the decision making process.
Keywords: sentiment analysis; review analysis; e-commerce; recommendation systems; multi-criteria decision making; MCDM; weighted sum method.
International Journal of Business Information Systems, 2020 Vol.35 No.2, pp.185 - 203
Received: 19 Feb 2018
Accepted: 10 Aug 2018
Published online: 08 Oct 2020 *