Multi-relational Graph Dataset for Yelp Spam Review Detection
Yelp-Fraud is a multi-relational graph dataset built upon the Yelp spam review dataset, which can be used in evaluating graph-based node classification, fraud detection, and anomaly detection models.
| # Nodes | %Fraud Nodes (Class=1) |
|---|---|
| 45,954 | 14.5 |
| Relation | # Edges |
|---|---|
| R-U-R | 49,315 |
| R-T-R | 573,616 |
| R-S-R | 3,402,743 |
| All | 3,846,979 |
The Yelp spam review dataset includes hotel and restaurant reviews filtered (spam) and recommended (legitimate) by Yelp. We conduct a spam review detection task on the Yelp-Fraud dataset which is a binary classification task. We take 32 handcrafted features from SpEagle paper as the raw node features for Yelp-Fraud. Based on previous studies which show that opinion fraudsters have connections in user, product, review text, and time, we take reviews as nodes in the graph and design three relations: 1) R-U-R: it connects reviews posted by the same user; 2) R-S-R: it connects reviews under the same product with the same star rating (1-5 stars); 3) R-T-R: it connects two reviews under the same product posted in the same month.
To download the dataset, please visit this Github repo. For any other questions, please email ytongdou(AT)gmail.com for inquiry.
Variants: Yelp-Fraud
This dataset is used in 2 benchmarks:
| Task | Model | Paper | Date |
|---|---|---|---|
| Fraud Detection | GTAN | Semi-supervised Credit Card Fraud Detection … | 2024-12-24 |
| Node Classification | GTAN | Semi-supervised Credit Card Fraud Detection … | 2024-12-24 |
| Fraud Detection | JA-GNN | Financial Fraud Detection using Jump-Attentive … | 2024-11-07 |
| Fraud Detection | BOLT-GRAPH | BOLT: An Automated Deep Learning … | 2023-03-30 |
| Node Classification | BOLT-GRAPH | BOLT: An Automated Deep Learning … | 2023-03-30 |
| Node Classification | RioGNN | Reinforced Neighborhood Selection Guided Multi-Relational … | 2021-04-16 |
| Fraud Detection | RioGNN | Reinforced Neighborhood Selection Guided Multi-Relational … | 2021-04-16 |
| Fraud Detection | GAT+JK | New Benchmarks for Learning on … | 2021-04-03 |
| Node Classification | GAT+JK | New Benchmarks for Learning on … | 2021-04-03 |
| Node Classification | CARE-GNN | Enhancing Graph Neural Network-based Fraud … | 2020-08-19 |
| Fraud Detection | CARE-GNN | Enhancing Graph Neural Network-based Fraud … | 2020-08-19 |
Recent papers with results on this dataset: