Spotting Suspicious Reviews via (Quasi-)clique Extraction

Abstract

How to tell if a review is real or fake? What does the underworld of fraudulent reviewing look like? Detecting suspicious reviews has become a major issue for many online services. We propose the use of a clique-finding approach to discover well-organized suspicious reviewers. From a Yelp dataset with over one million reviews, we construct multiple Reviewer Similarity graphs to link users that have unusually similar behavior: two reviewers are connected in the graph if they have reviewed the same set of venues within a few days. From these graphs, our algorithms extracted many large cliques and quasi-cliques, the largest one containing a striking 11 users who coordinated their review activities in identical ways. Among the detected cliques, a large portion contain Yelp Scouts who are paid by Yelp to review venues in new areas. Our work sheds light on their little-known operation.