A Survey on False Information Detection: From A Perspective of Propagation on Social Networks

2025-06-22

AI Summary

The proliferation of misinformation in the digital era necessitates robust and interpretable detection methods. This work addresses the problem by modeling information diffusion mechanisms, proposing the first unified classification framework for misinformation detection that integrates both homophilic and heterophilic propagation characteristics. We formalize the problem definition and systematically survey state-of-the-art models, benchmark datasets, and empirical performance limits. Methodologically, we synergize propagation dynamics modeling, graph neural networks, and multimodal natural language processing to uncover cross-platform diffusion patterns. Our key contributions are: (1) the first propagation-mechanism-driven unified classification framework; (2) a standardized benchmarking paradigm; and (3) advocacy for multimodal fusion and novel fact-checking tasks. The resulting reproducible and extensible research map advances misinformation detection toward joint optimization of efficiency, interpretability, and practical utility.

Technology Category

Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)Application Domains: Misinformation & Fake NewsMachine Learning: Multimodal Learning

Application Category

Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networksResponsible Web: Mitigating misinformation and disinformationWeb Mining and Content Analysis: Content-based information diffusion

Abstract

The proliferation of false information in the digital age has become a pressing concern, necessitating the development of effective and robust detection methods. This paper offers a comprehensive review of existing false information detection techniques, approached from a novel perspective that emphasizes the propagation characteristics of misinformation. We introduce a new taxonomy that categorizes these methods into homogeneous and heterogeneous propagation-based approaches, providing a deeper understanding of the varying scopes and complexities involved in information dissemination. For each category, we present a formal problem formulation, review commonly used datasets, and summarize state-of-the-art methods. Additionally, we identify several promising directions for future research, including the creation of a unified benchmark suite, exploration of diverse information modalities, and development of innovative rumor debunking tasks. By systematically organizing the vast array of current techniques, this work offers a clear overview of the research landscape, aiding researchers and practitioners in navigating this complex field and inspiring further advancements.

Problem

• Detecting false information propagation on social networks
• Reviewing existing detection techniques and propagation characteristics
• Proposing future research directions for rumor debunking

Innovation

• Propagation-based false information detection taxonomy
• Homogeneous and heterogeneous propagation analysis
• Unified benchmark suite for future research