Unsupervised Social Bot Detection via Structural Information Theory
arXiv:2404.13595 · doi:10.1145/3660522
Abstract
Research on social bot detection plays a crucial role in maintaining the order and reliability of information dissemination while increasing trust in social interactions. The current mainstream social bot detection models rely on black-box neural network technology, e.g., Graph Neural Network, Transformer, etc., which lacks interpretability. In this work, we present UnDBot, a novel unsupervised, interpretable, yet effective and practical framework for detecting social bots. This framework is built upon structural information theory. We begin by designing three social relationship metrics that capture various aspects of social bot behaviors: Posting Type Distribution, Posting Influence, and Follow-to-follower Ratio. Three new relationships are utilized to construct a new, unified, and weighted social multi-relational graph, aiming to model the relevance of social user behaviors and discover long-distance correlations between users. Second, we introduce a novel method for optimizing heterogeneous structural entropy. This method involves the personalized aggregation of edge information from the social multi-relational graph to generate a two-dimensional encoding tree. The heterogeneous structural entropy facilitates decoding of the substantial structure of the social bots network and enables hierarchical clustering of social bots. Thirdly, a new community labeling method is presented to distinguish social bot communities by computing the user's stationary distribution, measuring user contributions to network structure, and counting the intensity of user aggregation within the community. Compared with ten representative social bot detection approaches, comprehensive experiments demonstrate the advantages of effectiveness and interpretability of UnDBot on four real social network datasets.
42 pages, 12 figures, accepted for publication in Transactions on Information Systems
References in corpus (22)
- DeepWalk: Online Learning of Social Representations
- LINE: Large-scale Information Network Embedding
- Interpretable machine learning: definitions, methods, and applications
- The Rise of Social Bots
- The spread of low-credibility content by social bots
- Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models
- Bots increase exposure to negative and inflammatory content in online social systems
- Fame for sale: efficient detection of fake Twitter followers
- Arming the public with artificial intelligence to counter social bots
- The paradigm-shift of social spambots: Evidence, theories, and tools for the arms race
- Scalable and Generalizable Social Bot Detection through Data Selection
- A Decade of Social Bot Detection
- DNA-inspired online behavioral modeling and its application to spambot detection
- Social Fingerprinting: detection of spambot groups through DNA-inspired behavioral modeling
- BotRGCN: Twitter Bot Detection with Relational Graph Convolutional Networks
- SATAR: A Self-supervised Approach to Twitter Account Representation Learning and its Application in Bot Detection
- Its All in a Name: Detecting and Labeling Bots by Their Name
- RoSGAS: Adaptive Social Bot Detection with Reinforced Self-Supervised GNN Architecture Search
- SE-GSL: A General and Effective Graph Structure Learning Framework through Structural Entropy Optimization
- FedACK: Federated Adversarial Contrastive Knowledge Distillation for Cross-Lingual and Cross-Model Social Bot Detection
- BotShape: A Novel Social Bots Detection Approach via Behavioral Patterns
- USER: Unsupervised Structural Entropy-based Robust Graph Neural Network