A Macro- and Micro-Hierarchical Transfer Learning Framework for Cross-Domain Fake News Detection
Xuankai Yang, Yan Wang, Xiuzhen Zhang, Shoujin Wang, Huaxiong Wang, Kwok Yan Lam
TL;DR
This paper tackles cross-domain fake news detection under domain shift by identifying micro-level and macro-level transfer gaps. It introduces MMHT, comprising a Micro-Hierarchical Disentangling module that separates veracity-relevant from veracity-irrelevant content features and a Macro-Hierarchical Transfer Learning module that derives engagement features from common users across domains. The approach integrates disentangled content representations with user-engagement patterns through historical-news aggregation (GCN+Transformer) and yields a final veracity classifier. Extensive experiments on PolitiFact and GossipCop show MMHT consistently outperforms both single-domain and cross-domain baselines, with ablations confirming the contributions of the disentangling and engagement-transfer components. The work advances cross-domain fake news detection by enabling more accurate, transfer-efficient knowledge sharing across domains using both content and cross-domain user behavior.
Abstract
Cross-domain fake news detection aims to mitigate domain shift and improve detection performance by transferring knowledge across domains. Existing approaches transfer knowledge based on news content and user engagements from a source domain to a target domain. However, these approaches face two main limitations, hindering effective knowledge transfer and optimal fake news detection performance. Firstly, from a micro perspective, they neglect the negative impact of veracity-irrelevant features in news content when transferring domain-shared features across domains. Secondly, from a macro perspective, existing approaches ignore the relationship between user engagement and news content, which reveals shared behaviors of common users across domains and can facilitate more effective knowledge transfer. To address these limitations, we propose a novel macro- and micro- hierarchical transfer learning framework (MMHT) for cross-domain fake news detection. Firstly, we propose a micro-hierarchical disentangling module to disentangle veracity-relevant and veracity-irrelevant features from news content in the source domain for improving fake news detection performance in the target domain. Secondly, we propose a macro-hierarchical transfer learning module to generate engagement features based on common users' shared behaviors in different domains for improving effectiveness of knowledge transfer. Extensive experiments on real-world datasets demonstrate that our framework significantly outperforms the state-of-the-art baselines.