Mitigating Human and Computer Opinion Fraud via Contrastive Learning
This work addresses fake review detection in recommender systems, which is an incremental improvement by targeting both automated and human-generated fraud.
The paper tackles fake text review detection in collaborative filtering recommender systems by addressing both computer-generated and human-written fake reviews, using a contrastive learning architecture that incorporates user demographic characteristics and text reviews to improve robustness against biased reviews.
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.