Research map / Graph learning / Graph self-supervised learning
TwiBot-22: Towards Graph-Based Twitter Bot Detection
Shangbin Feng, Zhaoxuan Tan, Herun Wan, Ningnan Wang, Zilong Chen, Binchi Zhang, Qinghua Zheng, Wenqian Zhang, Zhenyu Lei, Shujie Yang, Xinshun Feng, Qingyue Zhang and 10 more
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add graph component (ablation) | BotRGCN · TwiBot-22 | accuracy: 75.4 -> 79.7 | Improved |
| add graph component (ablation) | BotRGCN · TwiBot-20 | accuracy: 82.6 -> 85.7 | Improved |
| add graph component (ablation) | RGT · TwiBot-20 | accuracy: 82.6 -> 86.6 | Improved |
| add graph component (ablation) | RGT · TwiBot-22 | accuracy: 75.4 -> 76.5 | Improved |
| add graph component (ablation) | BotRGCN · TwiBot-22 | F1: 41.2 -> 57.5 | Improved |
| add graph component (ablation) | GNN-based methods (BotRGCN, RGT) · TwiBot-20 and TwiBot-22 | accuracy | Improved |
| add graph component to a baseline (EvolveBot) (ablation) | EvolveBot · TwiBot-22 | accuracy: 71.1 -> 71.0 | No clear effect |
| use graph-based methods instead of feature/text-based | bot detection · TwiBot-20 and TwiBot-22 | accuracy | Improved |
| use higher-accuracy model (GAT vs LOBO) | bot detection generalization · TwiBot-22 sub-community folds | generalization avg accuracy: GAT avg lower by 2.55 than LOBO | Hurt |
Closest papers by meaning
- BotSim: LLM-Powered Malicious Social Botnet Simulation (AAAI 2025 · similarity 0.84)
- SeGA: Preference-Aware Self-Contrastive Learning with Prompts for Anomalous User Detection on Twitter (AAAI 2024 · similarity 0.83)
- A Multi-Task Benchmark for Abusive Language Detection in Low-Resource Settings (NeurIPS 2025 · similarity 0.82)
- Adversarial Socialbots Modeling Based on Structural Information Principles (AAAI 2024 · similarity 0.81)
- IOHunter: Graph Foundation Model to Uncover Online Information Operations (AAAI 2025 · similarity 0.81)
- Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards (ICML 2025 · similarity 0.81)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
