Spam Review Detection with Graph Convolutional Networks

TL;DR

This paper introduces a scalable graph convolutional network approach for detecting spam reviews on large online platforms, effectively addressing data scale and adversarial spammer tactics.

Contribution

The paper presents a novel GCN-based anti-spam model that integrates heterogeneous and homogeneous graphs for large-scale spam detection in online reviews.

Findings

Outperforms baseline models in offline experiments

Successfully deployed to process millions of reviews daily

Demonstrates effectiveness in real-world online environment

Abstract

Customers make a lot of reviews on online shopping websites every day, e.g., Amazon and Taobao. Reviews affect the buying decisions of customers, meanwhile, attract lots of spammers aiming at misleading buyers. Xianyu, the largest second-hand goods app in China, suffering from spam reviews. The anti-spam system of Xianyu faces two major challenges: scalability of the data and adversarial actions taken by spammers. In this paper, we present our technical solutions to address these challenges. We propose a large-scale anti-spam method based on graph convolutional networks (GCN) for detecting spam advertisements at Xianyu, named GCN-based Anti-Spam (GAS) model. In this model, a heterogeneous graph and a homogeneous graph are integrated to capture the local context and global context of a comment. Offline experiments show that the proposed method is superior to our baseline model in which the information of reviews, features of users and items being reviewed are utilized. Furthermore, we deploy our system to process million-scale data daily at Xianyu. The online performance also demonstrates the effectiveness of the proposed method.