Hits:
Journal:IEEE Transactions on Systems, Man, and Cybernetics: Systems（ABS 3星，中科院一区，FMS B类）
Key Words:Big Five personality, conflict quadrant diagram (CQD), consensus, group decision-making (GDM), large language models (LLMs).
Abstract: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.
Co-author:Jian Wu,Francisco Chiclana,Mi Zhou,Witold Pedrycz
First Author:Tiantian Gai
Indexed by:Journal paper
Discipline:Management Science
Document Type:J
Volume:55
Issue:11
Page Number:8506-8518
Translation or Not:no
Date of Publication:2025-10-17
Included Journals:SCI