From Risk Perception to Behavior Large Language Models-Based Simulation of Pandemic Prevention Behaviors

2026-01-07

arXiv.org

AI Summary

In the early stages of emerging infectious diseases, individual preventive behaviors exhibit high heterogeneity and are difficult to predict, particularly when empirical data are scarce and public health policies change rapidly. This work proposes a novel dynamic behavioral simulation framework grounded in large language models, integrating static behavioral intensity prediction with a dynamic risk-perception updating mechanism. By leveraging first-person structured prompt engineering, the framework simulates the evolution of residents’ protective behaviors over time. It supports zero-shot, few-shot, and cross-context transfer scenarios, achieving prediction accuracies of 72.7%, 81.8%, and 77.8%, respectively. The model successfully replicates behavioral shifts following China’s relaxation of pandemic control measures in December 2022, notably capturing the counterintuitive increase in low-friction behaviors such as disinfection. Its validity is further confirmed through Kolmogorov–Smirnov tests assessing consistency in behavioral distributions.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Individual prevention behaviors are a primary line of defense during the early stages of novel infectious disease outbreaks, yet their adoption is heterogeneous and difficult to forecast-especially when empirical data are scarce and epidemic-policy contexts evolve rapidly. To address this gap, we develop an LLM-based prevention-behavior simulation framework that couples (i) a static module for behavior-intensity prediction under a specified external context and (ii) a dynamic module that updates residents'perceived risk over time and propagates these updates into behavior evolution. The model is implemented via structured prompt engineering in a first-person perspective and is evaluated against two rounds of survey data from Beijing residents (R1: December 2020; R2: August 2021) under progressively realistic data-availability settings: zero-shot, few-shot, and cross-context transfer. Using Kolmogorov-Smirnov tests to compare simulated and observed behavior distributions (p>0.001 as the validity criterion), the framework demonstrates robust performance and improves with limited reference examples; reported predictive accuracy increases from 72.7% (zero-shot) to 81.8% (few-shot), and remains high at 77.8% under transfer to novel contexts. We further apply the framework to simulate behavior changes during China's December 2022 policy relaxation and to stress-test behavioral responses across 120 systematically varied epidemic conditions (R0, CFR, and control-measure tiers). Results indicate broad behavioral loosening under relaxation but a distinctive counter-trend increase in drain-related disinfection, highlighting how low-cost, low-friction behaviors may persist or intensify even when external constraints recede-raising a potential environmental tradeoff.

Problem

• risk perception
• prevention behavior
• behavioral heterogeneity
• pandemic response
• forecasting challenge

Innovation

• LLM-based simulation
• risk perception dynamics
• behavioral modeling
• prompt engineering
• cross-context transfer