DualMind: Towards Understanding Cognitive-Affective Cascades in Public Opinion Dissemination via Multi-Agent Simulation

TL;DR

DualMind is a multi-agent simulation platform that models the interaction between emotional responses and cognitive beliefs to improve forecasting of public opinion during crises, outperforming existing methods.

Contribution

We introduce DualMind, a novel LLM-driven multi-agent system that captures cognitive-affective cascades in public opinion dynamics during crises.

Findings

Accurately reconstructs opinion trajectories during real-world crises

Significantly outperforms state-of-the-art baselines in forecasting

Provides a high-fidelity tool for proactive crisis management

Abstract

Forecasting public opinion during PR crises is challenging, as existing frameworks often overlook the interaction between transient affective responses and persistent cognitive beliefs. To address this, we propose DualMind, an LLM-driven multi-agent platform designed to model this dual-component interplay. We evaluate the system on 15 real-world crises occurring post-August 2024 using social media data as ground truth. Empirical results demonstrate that DualMind faithfully reconstructs opinion trajectories, significantly outperforming state-of-the-art baselines. This work offers a high-fidelity tool for proactive crisis management. Code is available at https://github.com/EonHao/DualMind.