Dongguan Red Culture Communication Network Optimization Model Based on Graph Neural Network (GNN)

With the widespread adoption of social networks and the growing demand for the dissemination of red culture, optimizing the efficiency of its dissemination through modern technological approaches has become a critical challenge. This paper proposes an optimization model for red culture communication based on Graph Neural Networks (GNN), which aims to enhance the effectiveness and reach of red culture dissemination within social networks. The proposed model treats social network users as nodes and user interactions (such as likes, comments, and reposts) as edges in a graph structure. By leveraging the capabilities of GNN, the model captures intricate relationships between nodes, thereby improving the accuracy and range of information propagation. Comparative experiments demonstrate that the GNN-based model outperforms traditional propagation models, such as the Susceptible-Infected-Recovered (SIR) model and random propagation models, in terms of dissemination efficiency. Specifically, the GNN optimization resulted in a 25% increase in propagation range, an 18% enhancement in propagation speed, and a substantial improvement in information accuracy. These results underscore the potential of GNN for optimizing cultural communication processes in social networks.