Mitigating Human and Computer Opinion Fraud via Contrastive Learning

TL;DR

This paper presents a contrastive learning approach that combines user demographics and review texts to improve detection of fake reviews in recommender systems, addressing both machine-generated and user-generated spam.

Contribution

It introduces a novel contrastive learning architecture that leverages demographic data alongside review texts to enhance fake review detection.

Findings

Improved accuracy in identifying fake reviews.

Robustness against different types of review spam.

Enhanced system resilience to biased reviews.

Abstract

We introduce the novel approach towards fake text reviews detection in collaborative filtering recommender systems. The existing algorithms concentrate on detecting the fake reviews, generated by language models and ignore the texts, written by dishonest users, mostly for monetary gains. We propose the contrastive learning-based architecture, which utilizes the user demographic characteristics, along with the text reviews, as the additional evidence against fakes. This way, we are able to account for two different types of fake reviews spamming and make the recommendation system more robust to biased reviews.