Understanding Underground Incentivized Review Services
Rajvardhan Oak, Zubair Shafiq
TL;DR
This study investigates incentivized review fraud on e-commerce platforms from the perspective of the fraudsters themselves, using qualitative surveys of $N=36$ agents and $N=38$ jennies and a follow-up with $N=32$ agents after industry actions. It reveals a sophisticated, end-to-end ecosystem—spanning recruitment via Facebook groups, cross-platform communications, and off-platform reimbursements—where agents and buyers coordinate to source products, generate five-star reviews, and evade takedowns, often employing AI tools like ChatGPT to automate content. The authors assess takedown effectiveness, finding that platform interventions degrade recruitment channels and reduce activity but rarely eliminate the ecosystem, which adapts by migrating to backup channels and leveraging AI to generate and disguise content. They further show that coordinated legal actions, platform collaboration, and targeted countermeasures can reduce the prevalence of incentivized reviews, but the rapid evolution of tactics calls for ongoing auditing and multi-layer defenses. Overall, the work highlights the need for holistic detection strategies that combine technical signals with policy and legal action to curb underground incentivized review services and safeguard trust in reputation systems.
Abstract
While human factors in fraud have been studied by the HCI and security communities, most research has been directed to understanding either the victims' perspectives or prevention strategies, and not on fraudsters, their motivations and operation techniques. Additionally, the focus has been on a narrow set of problems: phishing, spam and bullying. In this work, we seek to understand review fraud on e-commerce platforms through an HCI lens. Through surveys with real fraudsters (N=36 agents and N=38 reviewers), we uncover sophisticated recruitment, execution, and reporting mechanisms fraudsters use to scale their operation while resisting takedown attempts, including the use of AI tools like ChatGPT. We find that countermeasures that crack down on communication channels through which these services operate are effective in combating incentivized reviews. This research sheds light on the complex landscape of incentivized reviews, providing insights into the mechanics of underground services and their resilience to removal efforts.