Coevolutionary Dynamics of Information and Influence in Social Networks

Abstract

The dynamic coupling between information propagation and individual influence diffusion in social networks is addressed by an influence–information coevolutionary propagation model. Grounded in non-Bayesian social learning theory, the model characterizes the mechanism through which individuals enhance their own influence by observing and imitating high-influence neighbors, and an susceptible–infected (SI)–susceptible (SIS) hybrid dynamical framework is employed to separately describe the irreversible information propagation process and the reversible influence learning process. By introducing an influence disparity-driven transmission rate function, the accelerating effect of high-influence individuals on information dissemination is quantified, together with the feedback enhancement effect of information propagation on individual influence. Numerical simulations and bounded public-data validation based on Sina Weibo propagation traces show that the initial seed’s influence significantly affects propagation speed, the dynamic influence update mechanism can reshape the influence distribution landscape in the network, and under the stated mean-field approximation, the coupling is associated with a lower effective early-growth bound. The robustness of these findings is further assessed through one-way parameter sensitivity analysis, comparison against five representative proxy/variant baseline models, confidence-interval estimation of the fitting accuracy, and cross-topology checks on public network datasets. This study provides a theoretical framework for understanding the coevolution of content dissemination and influence accumulation in social networks and has practical value in social media marketing strategy formulation and opinion leader identification.