SAHG: Sector-Anisotropic Hyperbolic Graph Model for Social Bot Detection

2026-05-28

AI Summary

Existing social bot detection methods exhibit limited performance when confronted with content generated by large language models (LLMs), and conventional graph neural networks struggle to model hierarchical, scale-free social graphs due to geometric distortions and disassortative connections. To address these challenges, this work proposes the Structure-Adaptive Hyperbolic Graph (SAHG) model, which leverages direction-dependent curvature fields and sector prototypes to achieve structure-aware geometric representations in hyperbolic space. SAHG further introduces a dual-channel hyperspherical graph neural network that separately encodes node-intrinsic features and neighborhood information, fusing them only at the classifier layer to effectively mitigate neighbor-induced feature contamination. Evaluated on three benchmarks—Fox8-23, BotSim-24, and MGTAB—SAHG consistently achieves state-of-the-art accuracy and F1 scores, significantly outperforming baselines based on handcrafted features, graph structures, LLMs, and isotropic hyperbolic embeddings.

Abstract

LLM-driven social bots can generate fluent, human-like text, reducing the discriminative advantage of content-based detection alone. However, coordinated campaigns still leave relational patterns -- interactions, behavioral similarity, shared neighborhoods, community positions, and coordinated activity -- that graph-based methods can exploit. Existing graph detectors face two challenges when exploiting such evidence. First, Euclidean GNNs distort hierarchical and scale-free social graphs; while hyperbolic geometry addresses this volume-growth mismatch, fixed-curvature models still assign uniform geometric resolution to structural directions with different densities and separation needs. Second, relational evidence is not always reliable: sophisticated bots forge heterophilic connections with genuine users, causing neighborhood aggregation to mix bot and human signals and dilute account-level evidence. We propose \textsc{SAHG} (Sector-Anisotropic Hyperbolic Graph), addressing both challenges. \textsc{SAHG} learns a direction-dependent curvature field $γ(u)$ that adapts geometric resolution across structural directions, and uses sector prototypes to convert angular concentration and alignment into classifier-readable features. To prevent contaminated aggregation from overwhelming account-level evidence, \textsc{SAHG} encodes per-account features and graph-neighborhood representations in two independent SAH channels, fusing them only at the classifier. Experiments on Fox8-23, BotSim-24, and MGTAB show that \textsc{SAHG} achieves the highest accuracy and F1 on all three benchmarks, outperforming feature-based, graph-based, LLM-based, and isotropic hyperbolic baselines. Ablation and geometric analyses confirm the effectiveness of the anisotropic geometry and dual-channel design.

Problem

• social bot detection
• hyperbolic graph
• anisotropic curvature
• relational evidence
• neighborhood aggregation

Innovation

• anisotropic hyperbolic geometry
• direction-dependent curvature
• dual-channel graph representation
• social bot detection
• sector prototypes