A social network group decision making framework with opinion dynamics considering opinion reliability

Opinion dynamics play an important role in the consensus reaching process (CRP) when tackling social network group decision making (SNGDM) problems. Opinion reliability can be regarded as an important characteristic of expert to indicate the reliability of experts' opinions in social trust network. However, it has rarely been considered into the opinion evolution process in SNGDM. To explore the impact of opinion reliability on group consensus reaching, a SNGDM framework with opinion dynamics considering opinion reliability is proposed in this paper. Firstly, opinion reliability of experts in social trust network is defined, and the comprehensive trust degree based on the social network structure and individual characteristic is proposed. Secondly, trust propagation and aggregation mechanisms are designed to obtain the social trust matrix. Thirdly, considering opinion similarity and opinion reliability, social network evolution rules and opinion evolution rules based on the extended Hegselmann-Krause (HK) model are presented. Finally, the proposal is applied to two numerical experiments about supplier performance evaluation and Zachary's karate club, and the simulation and comparison analyses are provided to demonstrate the convergence and illustrate the feasibility and effectiveness of the proposed model.