Mitigating Social Hazards: Early Detection of Fake News via Diffusion-Guided Propagation Path Generation

Litian Zhang, Xiaoming Zhang, Chaozhuo Li, Ziyi Zhou, Jiacheng Liu, Feiran Huang, Xi Zhang

Abstract: The detection of fake news has emerged as a pressing issue in the era of online social media. To detect meticulously fabricated fake news, propagation paths are introduced to provide nuanced social context to complement the pure semantics within news content. However, existing propagation-enhanced models face a dilemma between detection efficacy and social hazard. In this paper, we investigate the novel problem of early fake news detection via propagation path generation, capable of enjoying the merits of rich social context within propagation paths while alleviating potential social hazards. In contrast to previous discriminative detection models, we further propose a novel generative model, DGA-Fake, by simulating realistic propagation paths based on news content before actual spreading. A guided diffusion module is integrated into DGA-Fake to generate simulated user interaction sequences, guided by historical interactions and news content. Evaluation across three datasets demonstrates the superiority of our proposal. Our code is publicly available in https://anonymous.4open.science/r/DGA-Fake-1D5F/.

Primary Subject Area: [Experience] Multimedia Applications

Secondary Subject Area: [Experience] Multimedia Applications

Relevance To Conference: This work contributes to multimedia/multimodal processing by introducing an innovative approach to the detection of fake news within a multimodal social media environment. Specifically, it enhances the capacity to integrate the complex interplay of news content and network-based information by generating propagation paths through diffusion model. This methodology not only improves the understanding of how fake news disseminates across multimedia but also incorporates temporal dynamics to detect fake news. By capturing global propagation patterns through guided-diffusion model, the proposed DGA-Fake model adeptly navigates the multifaceted data environment typical of social media platforms. This allows for a effective integration of multimodal data sources, thereby improving the early detection of fake news while addressing potential social hazards associated with previous detection methods. Consequently, this work advances the field of multimedia processing by generate and integrate propagation path for processing and understanding the intricate modalities involved in social media content, thereby enhancing both the accuracy and efficiency of fake news detection in a multimodal context.

Submission Number: 2491