Problem
Research questions and friction points this paper is trying to address.
cognitive modules
opinion dynamics
agent-based modeling
vaccination
social influence
A Large Language Model-Driven Agent-Based Modeling Framework with Multi-Round Communication for Simulating Vaccine Opinion Dynamics
🤖 AI Summary
This study investigates how cognitive mechanisms drive individual vaccine decision-making and the dynamic evolution of collective opinions. To this end, we develop a multi-agent framework grounded in the Qwen3-8B large language model, incorporating—for the first time—a memory module and controlled prompt diversity, while integrating heterogeneous individual attributes and complex social network structures to simulate opinion dynamics through iterative interactions. The proposed approach successfully reproduces the nonlinear patterns of social influence observed in real-world settings, uncovers opposing effects of distinct cognitive mechanisms on group-level opinion formation, and demonstrates behavioral validity by meeting the tier-3 validation criteria for agent-based modeling.
📝 Abstract
Recently, Large Language Models (LLMs) have been utilized in various applications of computational social science and provide the possibility to integrate such models into agent-based modeling to explore the cognitive processes. However, how specific cognitive modules drive individual decisions and macro-level opinion dynamics remains unclear. Therefore, this study introduces a framework that integrates an LLM (Qwen3-8B) into agent-based modeling to investigate this problem, using vaccination opinion dynamics as a case study. We utilize this framework to simulate opinion dynamics among agents with heterogeneous profiles and social networks, evaluating scenarios by enabling different cognitive modules: a memory module and a prompt diversity module. The simulation results reveal that different cognitive modules have opposite impacts on our emergent opinion. Furthermore, the framework reproduces the non-linear behavior patterns of social influence observed in existing research, demonstrating our framework's validity and potential to reach the level 3 validation of agent-based models.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Large Language Model
Agent-Based Modeling
Cognitive Modules
Opinion Dynamics
Multi-Round Communication
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
