Towards Collusive Fraud Detection in Online Reviews

Online review fraud has evolved in sophistication by launching intelligent campaigns where a group of coordinated participants work together to deliver deceptive reviews for the designated targets. Such collusive fraud is considered much harder to defend against as these campaign participants are capable of evading detection by shaping their behaviors collectively so as not to appear suspicious. The present work complements existing studies by exploring more subtle behavioral trails connected with collusive review fraud. A novel statistical model is proposed to further characterize, recognize, and forecast collusive fraud in online reviews. The proposed model is completely unsupervised, which bypasses the difficulty of manual annotation required for supervised modeling. It is also highly flexible to incorporate collusion characteristics available for better modeling and prediction. Experiments on two real-world datasets demonstrate the effectiveness of the proposed method and the improvements in learning and predictive abilities.