The Spillover Effect of Fraudulent Reviews on Product Recommendations

As the prevalence of user-generated reviews has been growing, the pervasiveness of fraudulent reviews has been increasing as well. In an effort to alleviate the consequences of fraudulent reviews, platforms have been using machine-learning algorithms for fraudulent review detection. However, the current business practice of simply removing fraudulent reviews might not be sufficient, as even their temporary presence might forge spillover effects propagating through other shopping tools. In particular, we examine and discover the persistence of long-lasting significant adverse impact of fraudulent reviews through their propagation to recommender systems, even long after successfully detecting and removing all fraud incidents. We conduct additional analyses further examining the intensity and evolution of the spillover effect over time across different dimensions, such as the cost of the fraudulent activity, the effectiveness and timeliness of the detection algorithms, and the quality of products. The results illustrate the gravity of the identified effect and highlight that the current business practice of just removing the fraudulent reviews is insufficient in the presence of recommender systems, albeit potentially sufficient in their absence in the long run. Such findings are timely as they might inform current regulatory and policy discussions. Finally, we also design a simple remedy that can be easily introduced to collaborative filtering algorithms to debias the recommender systems and demonstrate its effectiveness in alleviating the impact of the identified spillover effect.