Mixed Deffuant Dynamics

Abstract

The original Deffuant model consists of a finite number of agents whose opinion is a number in $[0,1]$. Two socially connected agents are uniformly randomly selected at each time step and approach each other at a rate $\mu\in [0,1/2]$ if and only if their opinions differ by at most some confidence threshold $\epsilon>0$. In this paper, we consider a variant of the Deffuant model, namely the mixed model, where the convergence parameter $\mu$ and the social relationship can vary over time. We investigate circumstances under which asymptotic stability holds or a consensus can be achieved. Also, we derive a nontrivial lower bound for the probability of consensus which is independent of the number of agents.