A New Approach to Compute a Realistic Credibility Rank for Reviewers Using Fuzzy Inference

Online product review websites as one of the examples of Web ۲.۰ websites allow users share their ideas and opinions about various products and services. Although online reviews as a user-generated content can be considered as an invaluable source of information for both consumers and firms, these reviews vary greatly in term of quality and credibility. To tackle the problem of low quality reviews, we address reviewer credibility and propose a novel and feasible framework for ranking reviewers in terms of credibility. The proposed framework exploits four kinds of features including social network, profile, engagement and knowledge to quantify reviewer credibility dimensions and utilize a fuzzy inference system to calculate credibility scores of reviewers in a cognitive approach. To illustrate an application of the proposed method, we conduct an experimental study using real data gathered from Epinions. The proposed framework can support marketing departments in identifying the most credible reviewers.

Keywords:

Social Web , Online Reviews , Reviewer Credibility , Social Network , Shannon Entropy , Fuzzy Inference Systems