LAUSR

Significance Online reviews significantly impact consumers’ decisions and are seen as crucial to the success of online markets. Despite this, the prevalence of fake reviews is arguably higher than ever, despite two decades of academic research on identifying and regulating them. We use data in which we directly observe which products buy fake reviews, and study how to identify them. We show that products buying fake reviews are highly clustered in the product reviewer network, due to their reliance on common reviewers. This allows us to detect them with high accuracy using both supervised and unsupervised methods. Unlike approaches relying on reviews’ text, this approach is more robust to manipulation by sellers. Moreover, it is scalable and generalizable to many settings.