Fraudulent review detection model focusing on emotional expressions and explicit aspects: investigating the potential of feature engineering

摘要

Reading customer reviews before purchasing items online has become a common practice; however, some companies use machine learning (ML) algorithms to generate false reviews in order to create positive brand images of their own products and negative images of competitors' offerings. Existing techniques use review content to identify fraudulent reviewers; however, spammers become more intelligent, started to learn from their mistakes, and changed their tactics in order to avoid detection techniques. Thus, investigating fraudulent accounts' behaviour of generating fake negative or positive reviews for competitors or themselves and the necessity of ML classifiers to identify fraudulent reviews, is more important than ever. In this research, we present a novel feature engineering approach in which we (1) extract several “review-centric” and “reviewer-centric” features from a dataset; (2) combine the cumulative effects of features distributions into a unified model that represents overall behavior of the fraudulent reviewers; (3) investigate the role of effective data pre-processing to improve detection accuracy; and (4) develop a probabilistic approach to detect fraudulent reviewers by learning a novel M-SMOTE model over a derived balanced dataset and feature distributions, which outperforms other ML models. Our study contributes to the literature on digital platforms and fraudulent review detection with significant managerial and theoretical implications through these novel findings.