Working Paper

Detecting Fake Review Buyers Using Network Structure: Direct Evidence from Amazon

Sherry He

University of California, Los Angeles

Brett Hollenbeck

University of California, Los Angeles

Gijs Overgoor

Southern Methodist University

Davide Proserpio

University of Southern California

Ali Tosyali

Rochester Institute of Technology

Oct 26, 2022

Uses unsupervised machine learning to accurately identify fake review buyers by simply identifying clusters of products that are closely connected in a network. Because such clusters follow directly from the economics of fake review marketplaces, it is difficult for unscrupulous sellers to evade detection.

By using MSI.org you agree to our use of cookies as identifiers and for other features of the site as described in our Privacy Policy.