Temporal Neighbor Sequence-based Interpretable Spammer Groups Detection on E-commerce platform

Organized spammer groups collaborate to manipulate reviews for illicit gains, posing significant challenges to online platforms. This paper introduces a Temporal Neighbor Sequence-based Interpretable Spammer Group Detection method called TNSGD. First, we filter high-suspicious reviewers to reduce node complexity in the co-review temporal network, optimizing the detection process. Second, a co-review temporal network is constructed using these filtered reviewers, generating temporal neighbor sequences that capture temporal aggregation and relational features to form candidate groups. These candidate groups are then classified using group spam indicators and heuristic conditions to delineate the final spammer groups. TNSGD surpasses baseline methods with notable improvements in Precision and F1 scores, including enhancements of 4% and 3% for Amazon and 39% and 31% for Yelp, respectively. Additionally, TNSGD significantly reduces computational complexity to 1/85th and 1/7th. Furthermore, we provide interpretations of TNSGD from two perspectives: model and result. We devise a transparent detection process for model interpretation to ensure each step has a clear physical significance. For result interpretation, we offer interpretable visualizations of the temporal–spatial and evolutionary characteristics of the detected spammer groups, providing valuable insights for refining future detection models.