Tiantian Gai

In group decision-making (GDM), the opinions of decision-makers (DMs) are prone to having controversies and conflicts. Identifying individual personality traits can better predict the individual adjustment behavior of DMs in GDM and, therefore, construct the corresponding feedback strategies to guide opinion interaction and consensus building. To do that, large language models (LLMs) are utilized to analyze the individual Big Five personality traits revealed by online text information. Then, a conflict quadrant diagram (CQD) is developed to explore the conflict resolution behaviors manifested by DMs as influenced by their personality traits. Subsequently, a series of interaction rules corresponding to diverse conflict behaviors within the CQD are constructed, and then a personality traits-driven feedback model is proposed to generate personalized recommendation advice for group consensus interaction, with the overarching aim of effectively enhancing the level of group consensus. Finally, a simulation experiment on LLM-based agents is conducted to verify the opinion convergence process, and some sensitivity and comparative analyses are also provided. Overall, this article contributes to the innovative application of LLMs in solving GDM problems by prompt engineering to generate outputs and validate models and carries out in-depth explorations on integrating individual personality traits into the group consensus-building process.

The relationship between trust and consensus has long been a focal point in social network group decision-making (SN-GDM). This article investigates a two-stage feedback model for SN-GDM driven by a trust incentive mechanism, aimed at promoting expert collaboration and enhancing consensus levels. First, a trust path determination method is proposed by integrating trust score and social authority to identify the optimal trust propagation paths. Then, based on trust utility (TU), an improved Uninorm trust propagation operator is developed to better align with real-world SN-GDM scenarios. Next, a trust incentive mechanism is designed, incorporating cooperative behavior into a dynamic social trust network to construct a two-stage feedback model. The first stage is a minimum-cost consensus model, and the second is a maximum-consensus model, both constrained by the cooperation degree index (CDI). A social trust network correction mechanism is further introduced, with results showing that increased consensus enhances mutual trust among experts, thereby improving CDI values. Consequently, the proposed trust-incentive-driven two-stage feedback model effectively facilitates consensus building within expert groups. Compared with traditional feedback models, this approach better reflects the psychological dynamics of experts during the consensus-reaching process and further explores its applicability in practical decision-making contexts. Finally, the proposed model is applied to a real-world decision scenario and compared with other methods, demonstrating its effectiveness and applicability.

In the consensus reaching process (CRP) of social network group decision making, the noncooperative behavior exhibited by experts will hinder the achievement of group consensus. This article develops a noncooperative behavior management framework based on trust propagation and dynamic cooperation index under bidirectional feedback context. On the one hand, a trust propagation operator with trust decay is established to enhance the trust relationship between noncooperative experts. On the other hand, the fuzzy preference relations are utilized as preference expression structure, and the mutual reinforcing effect between consensus and trust is explored to achieve the dynamic enhancement of cooperation index, thereby facilitating the transformation of nonscooperative behavior. Specifically, a cooperation index is formulated to identify the noncooperation behavior. Subsequently, a noncooperative behavior transformation method by dynamic cooperation index is investigated. Finally, a bidirectional feedback mechanism is provided for group consensus reaching. This paper provides an innovative strategy for detecting and managing noncooperative behavior, an illustrative example and some analyses are presented to verify the validity of proposed method.

In social network group decision making (SN-GDM), overlapping communities are special community structures that can assist opinion interaction to reach group consensus. However, the specific mechanisms of how overlapping structures facilitate community interaction need to be further explored. In addition, the compromise behavior of decision makers (DMs) is conducive to group consensus, but it is usually fixed at the same value, and then it need further research the characteristic of the dynamics compromise limits. To this end, the overlapping community structures under DMs’ trust network is detected. Then, the effect of community overlap in social networks on community interaction is explored. Meanwhile, a limited compromise function is built based on prospect theory to describe the dynamic compromise behavior of communities. Hence, a dynamic compromise behavior driven bidirectional feedback mechanism with overlapping communities is proposed in the context of SN-GDM, and an illustrative example with comparative analysis is provided to testify the advantages of proposed method. It is proved that overlapping communities can improve the compromise willingness compared to nonoverlapping communities, indicating that overlapping communities can serve as a bridge to facilitate interaction, and the dynamic compromise behavior can more realistically describe the real behavior of DMs. In general terms, the proposed method provides a solution to the consensus reaching issue of SN-GDM from a new perspective. Specifically, it can be applied to real-life application scenarios, such as group recommendation to recommend acceptable solutions for social network group users.

Supply chain finance (SCF) can provide innovative financing approaches for cash-constrained supply chain partners, which has been utilized for industries to optimize capital, reduce costs and alleviate financing pressure. Despite there are promising results in SCF, there are still many challenges in the development of SCF practice, such as the information asymmetry problem and credit data transmission barriers. Blockchain has been widely adopted in the finance industry, it can provide solutions to these challenges. However, the capabilities and performance of different blockchain platforms (BPs) vary greatly, thus, it is necessary to select an appropriate BP according to the specific circumstances of SCF. The main purpose of this article is to develop a decision-making framework to select a suitable BP for the blockchain implementation of SCF. Since SCF business involves multiple entities such as core enterprises, suppliers, and financial institutions, each entity has different requirements for BP, so conflicts of opinion are prone to occur in the decision making process. To this end, we develop a bilateral negotiation group multiattribute decision making (BN-GMADM) method with personalized individual semantics (PIS) to coordinate opinions and promote consensus. In addition, the distributed linguistic scoring rule (DLSR) is proposed for BP alternatives scoring and ranking. A case study and several analyses are provided to illustrate and validate the proposed approach.