Fraudulent Review Detection Model Focusing On Emotional Expressions And Explicit Aspects: Investigating The Potential Of Feature Engineering

Ajay Kumar (Emlyon Business School, France), Pei-yu Chen (Arizona State University, USA), Ram Gopal (Warwick Business School, UK)

Reading customer reviews before purchasing any items online has become a common practice around the world. Existing methods use review content to identify the fake reviewers and their behavior; however, spammers became more intelligent, started to learn from their mistakes, and changed their tactics when writing fake reviews in an attempt to avoid detection techniques. Thus, investigating fake accounts’ behavior of generating fake negative or positive reviews for competitors or themselves and the necessity of ML classifiers to identify fake reviews, is more important than ever. In this research, we present a novel feature engineering approach for this task in which we extract several “review-centric” and “reviewer-centric” features from the dataset and develop a probabilistic approach to detect fake reviewers over derived balanced dataset and feature distributions, which outperforms other existing ML models.