Unified Representation and Game-Theoretic Modelling of Online Rumour Diffusion

Abstract

Rumour propagation in online social networks poses significant risks to public trust, economic stability, and crisis management. Existing models often struggle with heterogeneous feature spaces, adversarial dynamics between rumours and debunking information, and data sparsity in early outbreak stages. This study introduces a cross-domain framework for group behaviour prediction that integrates unified representation learning, game-theoretic adversarial modelling, and transfer adaptation. A hybrid BERT–Node2Vec encoder captures both semantic richness and structural influence, while evolutionary game theory quantifies competitive interactions between rumour-spreaders and refuters. To alleviate data scarcity, Joint Distribution Adaptation (JDA) aligns heterogeneous feature spaces across domains, enabling robust transfer learning. Evaluated on simulated and real-world social media datasets, the proposed model demonstrates improved accuracy and interpretability in predicting rumour diffusion trends under adversarial conditions. These findings highlight the value of integrating semantic, structural, and behavioural signals into a scalable architecture, offering a practical solution for safeguarding digital ecosystems against misinformation.