Social bot detection improves by balancing model simplicity and conflict awareness
CSC: Calibrated Simplicity for Conflict-Aware Social Bot Detection in the LLM Era
Machine Learning
Summary
It is hard to spot fake social media accounts because smart AI can make their posts look very real. The authors found that just making detection models more complex does not always help. They created a method called CSC that keeps the model simple and carefully combines different clues, like how an account connects with others and if its profile matches its posts. Their approach makes deciding if an account is a bot more reliable, even when the bot tries to hide by copying human writing.
What this means in practice
- •For social media platform engineers: Improve bot detection tools by integrating simple graph models with calibrated fusion to better identify sophisticated fake accounts.
- •For online security analysts: Enhance monitoring systems to flag accounts with mismatched text and network patterns, catching bots that mimic human language.
Authors
Yipeng Qian, Pengjie Zhao, Chaoxi Niu
Abstract
Social bot detection is essential for protecting online platforms from misinformation amplification, coordinated manipulation, and distorted public discourse. However, large language models have made social bots much harder to detect from text alone because semantic camouflage is now cheap, fluent, and scalable. The resulting challenge is modality conflict: an account may look human-like in semantics while remaining suspicious in graph structure, profile attributes, or cross-modal consistency. Recent graph-based detectors tackle this limitation by adding graph-side complexity, such as sparse prototype selection, adaptive gating, or architecture-specific control logic, yet our experiments suggest that complexity alone is not the most reliable way to resolve such conflict. We therefore propose CSC, a calibrated-simplicity framework for conflict-aware LLM-era social bot detection. The framework combines three design choices: a simplified prototype-guided graph expert that retains useful structural biases while removing unstable graph-side heuristics, calibrated simplex-constrained fusion that aligns heterogeneous confidence spaces before late fusion, and a lightweight inconsistency expert that models cross-modal disagreement. Experiments on TwiBot-22, TwiBot-20, and MGStBot-large show that \textsc{CSC} improves calibrated operating-point decision quality while remaining competitive across external benchmarks. Further analyses show that calibration improves confidence reliability, the inconsistency expert mainly provides localized corrections in high-conflict or near-threshold regions, and simplified graph-side control yields a better stability-cost trade-off. A targeted semantic-camouflage stress test further shows that replacing selected bot text with matched human text sharply degrades the standalone text expert while leaving graph and fused evidence stable on a balanced challenge set.