PRISM: A Personality-Driven Multi-Agent Framework for Social Media Simulation
This provides a robust tool for analyzing complex social media ecosystems, addressing the need to capture psychological heterogeneity in online polarization.
The paper tackled the problem of simplistic homogeneity in agent-based models of opinion dynamics by introducing PRISM, a hybrid framework that couples stochastic differential equations with personality-conditional POMDPs, achieving superior personality consistency aligned with human ground truth and outperforming standard benchmarks.
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.