Modeling Multi-source Information Diffusion: A Graphical Evolutionary Game Approach

Abstract

Modeling of information diffusion over social networks is of crucial importance to better understand how the avalanche of information overflow affects our social life and economy, thus preventing the detrimental consequences caused by rumors and motivating some beneficial information spreading. However, most model-based works on information diffusion either consider the spreading of one single message or assume different diffusion processes are independent of each other. In real-world scenarios, multi-source correlated information often spreads together, which jointly influences users' decisions. In this paper, we model the multi-source information diffusion process from a graphical evolutionary game perspective. Specifically, we model users' local interactions and strategic decision making, and analyze the evolutionary dynamics of the diffusion processes of correlated information, aiming to investigate the underlying principles dominating the complex multi-source information diffusion. Simulation results on synthetic and Facebook networks are consistent with our theoretical analysis. We also test our proposed model on Weibo user forwarding data and observe a good prediction performance on real-world information spreading process, which demonstrates the effectiveness of the proposed approach.