BotRGCN: Twitter Bot Detection with Relational Graph Convolutional Networks
arXiv:2106.13092 · doi:10.1145/3487351.3488336
Abstract
Twitter bot detection is an important and challenging task. Existing bot detection measures fail to address the challenge of community and disguise, falling short of detecting bots that disguise as genuine users and attack collectively. To address these two challenges of Twitter bot detection, we propose BotRGCN, which is short for Bot detection with Relational Graph Convolutional Networks. BotRGCN addresses the challenge of community by constructing a heterogeneous graph from follow relationships and applies relational graph convolutional networks. Apart from that, BotRGCN makes use of multi-modal user semantic and property information to avoid feature engineering and augment its ability to capture bots with diversified disguise. Extensive experiments demonstrate that BotRGCN outperforms competitive baselines on a comprehensive benchmark TwiBot-20 which provides follow relationships.
arXiv commentaccepted at ASONAM 2021
References in corpus (9)
- Semi-Supervised Classification with Graph Convolutional Networks
- BotOrNot: A System to Evaluate Social Bots
- Deep Neural Networks for Bot Detection
- Disinformation and Social Bot Operations in the Run Up to the 2017 French Presidential Election
- Scalable and Generalizable Social Bot Detection through Data Selection
- A Decade of Social Bot Detection
- TwiBot-20: A Comprehensive Twitter Bot Detection Benchmark
- DNA-inspired online behavioral modeling and its application to spambot detection
- Twitter Bot Detection Using Bidirectional Long Short-term Memory Neural Networks and Word Embeddings
Cited by in corpus (5)
- A Comprehensive Survey on Deep Graph Representation Learning
- GAD-NR: Graph Anomaly Detection via Neighborhood Reconstruction
- Unsupervised Social Bot Detection via Structural Information Theory
- Simplistic Collection and Labeling Practices Limit the Utility of Benchmark Datasets for Twitter Bot Detection
- Multimodal Detection of Bots on X (Twitter) using Transformers