An Opinion Dynamics Model with Increasing Self-Confidence

We propose an opinion dynamics model in which agents gradually increase their own self-confidence while interacting with each other. The relations between the newly proposed model and existing works of social learning, inertial opinion dynamics, Bayesian inference, and stochastic multi-armed bandits are demonstrated. We prove the convergence of the system with the existence of a truth under fixed and periodically changing social networks, and obtain tight convergence bounds related to the spectral gap of the graph Laplacian and the maximum total degree centrality, respectively. In the case of randomly generated social networks, an almost-sure convergence result is obtained. The dynamics of the model with multiple truths or zero truth is also discussed.