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

2026-01-28

AI Summary

This study addresses the limitation of existing public opinion prediction methods, which often overlook the dynamic interplay between affective responses and cognitive beliefs, thereby failing to accurately capture opinion dynamics during crisis events. To overcome this, the authors propose the first large language model–driven multi-agent simulation framework that integrates a dual-channel cognitive-affective mechanism. By modeling individuals’ dual psychological processes in crisis scenarios, the framework dynamically reconstructs the trajectory of public opinion propagation. Trained and validated on real-world social media data, the approach significantly outperforms state-of-the-art baselines across fifteen real crisis events occurring after August 2024, achieving higher-fidelity opinion reconstruction and more accurate forward-looking predictions, thus offering robust support for crisis communication and decision-making.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Knowledge Representation and Reasoning: Preferences

Application Category

• Web Mining and Content Analysis: Sentiment analysis and opinion mining
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Social Networks and Social Media: Media and governance, opinion dynamics, filter bubbles, polarization

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.

Problem

• public opinion
• cognitive-affective interaction
• PR crises
• opinion dissemination
• affective responses

Innovation

• cognitive-affective cascades
• multi-agent simulation
• LLM-driven modeling
• public opinion forecasting
• crisis communication