Virtual communities are characterized by complex and dynamic interaction patterns among heterogeneous users and content. We focus on virtual communities because they present unique challenges, including diverse user types, multiple interaction modalities, and rapidly evolving network structures, which make predicting community-network evolution particularly complex and valuable. Accurately predicting the evolution of these interactions is crucial for effective community management and user engagement. In this paper, we propose DHGEP, a Dynamic Heterogeneous Graph Evolution Predictor, which leverages graph learning techniques to model and forecast the temporal evolution of virtual community interaction networks. DHGEP constructs a heterogeneous graph representing various user types, content, and interaction relationships, and employs a dynamic graph neural network enhanced with adaptive attention mechanisms to capture both structural and temporal dependencies. Experimental results on simulated and real-world community datasets demonstrate that DHGEP significantly outperforms baseline methods in predicting future interactions, providing a practical tool for proactive community management and insight-driven decision making.
Wang et al. (Thu,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: