PRISM: 一种基于个性的多智能体框架用于社交媒体模拟
PRISM: A Personality-Driven Multi-Agent Framework for Social Media Simulation
AI总结：
PRISM通过结合连续情绪演变与基于个性的决策过程，提供了一种更准确模拟社交媒体中个性驱动意见极化的框架。
摘要：
传统意见动力学的基于代理模型（ABMs）往往由于对在线极化驱动的心理异质性假设过于简单而无法捕捉到。这种局限性掩盖了个体认知偏差与信息传播之间的关键互动，从而阻碍了对意识形态分歧如何被放大机制的理解。为了解决这一挑战，我们引入了Personality-Refracted Intelligent Simulation Model（PRISM），一种将随机微分方程（SDE）用于连续情绪演变与基于个性的条件部分可观测马尔可夫决策过程（PC-POMDP）用于离散决策制定相结合的混合框架。与连续特质方法不同，PRISM为多模态大语言模型（MLLM）代理分配了基于迈尔斯-布里格斯类型指标（MBTI）的认知策略，这些策略通过从大规模社交媒体数据集中的数据驱动先验初始化。PRISM实现了与人类地面真相一致的优越个性一致性，显著优于标准同质和大五维度基准。该框架有效复制了诸如理性压制和情感共鸣等新兴现象，为分析复杂的社交媒体生态系统提供了稳健的工具。
英文摘要：
Traditional agent-based models (ABMs) of opinion dynamics often fail to capture the psychological heterogeneity driving online polarization due to simplistic homogeneity assumptions. This limitation obscures the critical interplay between individual cognitive biases and information propagation, thereby hindering a mechanistic understanding of how ideological divides are amplified. To address this challenge, we introduce the Personality-Refracted Intelligent Simulation Model (PRISM), a hybrid framework coupling stochastic differential equations (SDE) for continuous emotional evolution with a personality-conditional partially observable Markov decision process (PC-POMDP) for discrete decision-making. In contrast to continuous trait approaches, PRISM assigns distinct Myers-Briggs Type Indicator (MBTI) based cognitive policies to multimodal large language model (MLLM) agents, initialized via data-driven priors from large-scale social media datasets. PRISM achieves superior personality consistency aligned with human ground truth, significantly outperforming standard homogeneous and Big Five benchmarks. This framework effectively replicates emergent phenomena such as rational suppression and affective resonance, offering a robust tool for analyzing complex social media ecosystems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
