Mining the Social Fabric: Unveiling Communities for Fake News Detection in Short Videos

2025-08-11

AI Summary

Detecting fake news in short videos faces challenges stemming from fragmented multimodal information and insufficient contextual cues; existing approaches predominantly rely on unimodal content analysis, neglecting implicit associations among videos, uploaders, and events. To address this, we propose a dual-community graph modeling framework: (1) constructing a heterogeneous temporal graph comprising an uploader community and an event-driven community; (2) designing a temporal-aware graph attention network; and (3) incorporating a reconstruction-based pretraining objective to optimize node representations. To our knowledge, this is the first work to explicitly model social propagation structures as two interdependent communities, substantially enhancing cross-entity relational reasoning. Extensive experiments on multiple public benchmarks demonstrate that our method consistently outperforms state-of-the-art approaches, validating the effectiveness of the dual-community structure in improving both detection accuracy and generalization capability.

Technology Category

• Computer Vision: Multi-modal Vision
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks

Abstract

Short video platforms have become a major medium for information sharing, but their rapid content generation and algorithmic amplification also enable the widespread dissemination of fake news. Detecting misinformation in short videos is challenging due to their multi-modal nature and the limited context of individual videos. While recent methods focus on analyzing content signals-visual, textual, and audio-they often overlook implicit relationships among videos, uploaders, and events. To address this gap, we propose DugFND (Dual-community graph for fake news detection), a novel method that enhances existing video classifiers by modeling two key community patterns: (1) uploader communities, where uploaders with shared interests or similar content creation patterns group together, and (2) event-driven communities, where videos related to the same or semantically similar public events form localized clusters. We construct a heterogeneous graph connecting uploader, video, and event nodes, and design a time-aware heterogeneous graph attention network to enable effective message passing. A reconstruction-based pretraining phase further improves node representation learning. DugFND can be applied to any pre-trained classifier. Experiments on public datasets show that our method achieves significant performance gains, demonstrating the value of dual-community modeling for fake news detection in short videos.

Problem

• Detecting fake news in short videos is challenging due to multi-modal content and limited context.
• Existing methods overlook implicit relationships among videos, uploaders, and events.
• Proposing DugFND to model uploader and event-driven communities for improved fake news detection.

Innovation

• Dual-community graph modeling for fake news detection
• Time-aware heterogeneous graph attention network
• Reconstruction-based pretraining for node representation