Higher-order rumor and anti-rumor propagation and data-driven optimal control on hypergraphs

To address the “explosive” propagation phenomenon in social networks, we propose a novel hypergraph propagation model that captures the higher-order interaction process between rumor and anti-rumor. By calculating the propagation threshold and analyzing the global stability of equilibrium points, our research indicates that the higher-order structure is a component of the propagation threshold, directly affecting the final state of the propagation dynamics. Additionally, we design data-driven control algorithms, which integrates deep neural networks and ensemble learning algorithms, to autonomously seek suboptimal control strategies for rumor within the framework of optimal control theory. This approach enhances the efficiency and adaptability of traditional control methods. Simulation experiments demonstrate that the control algorithm effectively regulates rumor propagation, achieving a control cost deviation of only 0.0016 from the optimal control theory, while substantially improving the control speed compared to conventional methods.