Evaluating Online Products Using Text Mining: A Reliable Evidence-Based Approach

Abstract

To address the uncertainty about the quality of online merchandise, e-commerce sites often provide product review ranking services to help customers make purchasing decisions. Such services can be very useful, but they are not necessarily reliable when the ranking results are based on ratings without considering their reliability. In this paper, we propose a reliable evidence-based approach to online product evaluation by using text mining to analyze product reviews while taking into account the reliability of each review. We parse the product reviews and classify the opinion orientations for each recognized product feature as positive or negative. Then, we weigh the classified opinion orientations by their reliability and use them as independent evidence to calculate the belief values of the product using Dempster–Shafer (DS) theory. Based on the belief values of a list of similar products, we can calculate their product effectiveness and cost-effectiveness values for product ranking. The case studies show that our approach can greatly help customers make better decisions when choosing the right online products.