Evolution of Malicious Social Bot Detection: From Individual Profiling to Group Analysis and Beyond
Authors:
- 1 September 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Journal of Social Computing
- Vol. 6 (3) , 258-284
Abstract
The rise of online social platforms has enhanced connectivity and access to information. Still, it has also enabled the proliferation of malicious social bots that threaten platform security and disrupt social order. In this paper, we introduce a unified framework for defining and classifying malicious social bots along three dimensions: behavior, interaction, and operation. We then present a comprehensive review of social bot detection methods, tracing their evolution from traditional machine learning techniques to deep learning architectures and graph neural networks, with particular emphasis on recent advances in group-level detection. We also explore the emerging paradigm of Large Language Model (LLM) based bot detection. This paper reviews the current state of research, identifies key challenges, and outlines future directions. It provides a cohesive foundation for building more robust detection frameworks to counter the evolving threats posed by malicious social bots.Keywords
Funding Information
- National Natural Science Foundation of China (62302213)
- Dalian University of Technology
This publication has 122 references indexed in Scilit:
- BotSCL: Heterophily-Aware Social Bot Detection with Supervised Contrastive Learning2024
- BotRGA: Neighborhood-Aware Twitter Bot Detection with Relational Graph Aggregation2024
- BotCL: a social bot detection model based on graph contrastive learningKnowledge and Information Systems, 2024
- Conclusion: Misinformation and AI—How Algorithms Generate and Manipulate Misinformation2024
- Bot Detection on Online Social Networks Using Deep Forest2019
- Arming the public with artificial intelligence to counter social botsHuman Behavior and Emerging Technologies, 2019
- Its all in a name: detecting and labeling bots by their nameComputational and Mathematical Organization Theory, 2018
- Discovering Opinion Spammer Groups by Network Footprints2015
- Detecting Spamming Groups in Social Media Based on Latent Graph2015
- ND-Sync: Detecting Synchronized Fraud Activities2015