CoChat
Sign Up
Cited by 10Disaster Management and ResilienceEvacuation and Crowd DynamicsRisk Perception and Management

The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.

Multi-Stage Simulation of Residents’ Disaster Risk Perception and Decision-Making Behavior: An Exploratory Study on Large Language Model-Driven Social–Cognitive Agent Framework

Open access
Zhao, Xinjie, Wang, Hao, Dai, Chengxiao, Tang, Jiacheng, Deng, Kaixin, Zhong, Zhihua, Kong, Fanying, Wang, Shiyun, Morikawa, So·2025·Systems
DOI 10.3390/systems13040240
Open this paper in CoChat — free account

Abstract

The escalating frequency and complexity of natural disasters highlight the urgent need for deeper insights into how individuals and communities perceive and respond to risk information. Yet, conventional research methods—such as surveys, laboratory experiments, and field observations—often struggle with limited sample sizes, external validity concerns, and difficulties in controlling for confounding variables. These constraints hinder our ability to develop comprehensive models that capture the dynamic, context-sensitive nature of disaster decision-making. To address these challenges, we present a novel multi-stage simulation framework that integrates Large Language Model (LLM)-driven social–cognitive agents with well-established theoretical perspectives from psychology, sociology, and decision science. This framework enables the simulation of three critical phases—information perception, cognitive processing, and decision-making—providing a granular analysis of how demographic attributes, situational factors, and social influences interact to shape behavior under uncertain and evolving disaster conditions. A case study focusing on pre-disaster preventive measures demonstrates its effectiveness. By aligning agent demographics with real-world survey data across 5864 simulated scenarios, we reveal nuanced behavioral patterns closely mirroring human responses, underscoring the potential to overcome longstanding methodological limitations and offer improved ecological validity and flexibility to explore diverse disaster environments and policy interventions. While acknowledging the current constraints, such as the need for enhanced emotional modeling and multimodal inputs, our framework lays a foundation for more nuanced, empirically grounded analyses of risk perception and response patterns. By seamlessly blending theory, advanced LLM capabilities, and empirical alignment strategies, this research not only advances the state of computational social simulation but also provides valuable guidance for developing more context-sensitive and targeted disaster management strategies.

Overview

Integrity signals

Registry

Crossref · 10.3390/systems13040240

Cites

7 of 7 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 7 references

Research works printed but not linked: 82

  1. Sitkin, 1992, Reconceptualizing the determinants of risk behavior, Acad. Manag. Rev., 17, 9, 10.2307/258646 · DOI · Paper page
  2. Parsons, 2016, Top-down assessment of disaster resilience: A conceptual framework using coping and adaptive capacities, Int. J. Disaster Risk Reduct., 19, 1, 10.1016/j.ijdrr.2016.07.005 · DOI
  3. Buchanan, 2013, Researching tomorrow’s crisis: Methodological innovations and wider implications, Int. J. Manag. Rev., 15, 205, 10.1111/ijmr.12002 · DOI
  4. Burger, A., Oz, T., Kennedy, W.G., and Crooks, A.T. (2019). Computational social science of disasters: Opportunities and challenges. Future Internet, 11. · DOI
  5. Cai, 2023, Influences of social environment and psychological cognition on individuals’ behavioral intentions to reduce disaster risk in geological hazard-prone areas: An application of social cognitive theory, Int. J. Disaster Risk Reduct., 86, 103546, 10.1016/j.ijdrr.2023.103546 · DOI
  6. Feng, 2021, Data collection methods for studying pedestrian behaviour: A systematic review, Build. Environ., 187, 107329, 10.1016/j.buildenv.2020.107329 · DOI
  7. Henderson, 1980, The influence of decision style on decision making behavior, Manag. Sci., 26, 371, 10.1287/mnsc.26.4.371 · DOI
  8. Zhao, X., Wang, S., and Wang, H. (2022). Organizational geosocial network: A graph machine learning approach integrating geographic and public policy information for studying the development of social organizations in China. ISPRS Int. J. Geo-Inf., 11. · DOI
  9. Ma, J. (2024). Can Machines Think Like Humans? A Behavioral Evaluation of LLM-Agents in Dictator Games. arXiv. · DOI
  10. Zhao, X., Blum, M., Yang, R., Yang, B., Carpintero, L.M., Pina-Navarro, M., Wang, T., Li, X., Li, H., and Fu, Y. (2024). AGENTiGraph: An Interactive Knowledge Graph Platform for LLM-based Chatbots Utilizing Private Data. arXiv.
  11. Fischhoff, 1993, Risk perception and communication, Annu. Rev. Public Health, 14, 183, 10.1146/annurev.pu.14.050193.001151 · DOI
  12. Conner, M., and Norman, P. (1996). Protection motivation theory. Predicting Health Behaviour: Research and Practice with Social Cognition Models, Open University Press.
  13. Cialdini, 2004, Social influence: Compliance and conformity, Annu. Rev. Psychol., 55, 591, 10.1146/annurev.psych.55.090902.142015 · DOI · Paper page
  14. Simon, H.A. (1997). Models of Bounded Rationality: Empirically Grounded Economic Reason, MIT Press. · DOI
  15. Tversky, A., Kahneman, D., and Slovic, P. (1982). Judgment Under Uncertainty: Heuristics and Biases, Cambridge University Press. · DOI · Paper page
  16. Ajzen, I. (1985). From Intentions to Actions: A Theory of Planned Behavior, Springer. · DOI · Paper page
  17. Beratan, 2007, A cognition-based view of decision processes in complex social–ecological systems, Ecol. Soc., 12, 27, 10.5751/ES-02103-120127 · DOI
  18. Liu, L. (2023). Study on Factors Influencing Public Risk Perception in Urban Heavy Rain and Flood Disasters. [Ph.D. Dissertation, Party School of the Central Committee of the C.P.C. (National Academy of Governance)].
  19. Williams, 2007, How does our perception of risk influence decision-making? Implications for the design of risk information, Theor. Issues Ergon. Sci., 8, 1, 10.1080/14639220500484419 · DOI · Paper page
  20. Giardini, 2021, Opinion dynamics and collective risk perception: An agent-based model of institutional and media communication about disasters, JASSS—J. Artif. Soc. Soc. Simul., 24, 4, 10.18564/jasss.4479 · DOI
  21. Wei, 2016, The evolution of stakeholders’ perceptions of disaster: A model of information flow, J. Assoc. Inf. Sci. Technol., 67, 441, 10.1002/asi.23386 · DOI
  22. Xu, 2016, Influences of mass monitoring and mass prevention systems on peasant households’ disaster risk perception in the landslide-threatened Three Gorges Reservoir area, China, Habitat Int., 58, 23, 10.1016/j.habitatint.2016.09.003 · DOI
  23. Antronico, L., Coscarelli, R., De Pascale, F., and Condino, F. (2019). Social perception of geo-hydrological risk in the context of urban disaster risk reduction: A comparison between experts and population in an area of Southern Italy. Sustainability, 11. · DOI
  24. Sampson, 1999, A cognitive information processing approach to employment problem solving and decision making, Career Dev. Q., 48, 3, 10.1002/j.2161-0045.1999.tb00271.x · DOI
  25. Suarez, 2024, Integrated decision support for disaster risk management: Aiding preparedness and response decisions in wildfire management, Inf. Syst. Res., 35, 609, 10.1287/isre.2022.0118 · DOI
  26. Jordan, 2021, Risk perception and culture: Implications for vulnerability and adaptation to climate change, Disasters, 45, 424, 10.1111/disa.12429 · DOI
  27. Kasperson, 1988, The social amplification of risk: A conceptual framework, Risk Anal., 8, 177, 10.1111/j.1539-6924.1988.tb01168.x · DOI · Paper page
  28. Bentley, 2014, Mapping collective behavior in the big-data era, Behav. Brain Sci., 37, 63, 10.1017/S0140525X13000289 · DOI
  29. Fekete, A., and Rhyner, J. (2020). Sustainable digital transformation of disaster risk—Integrating new types of digital social vulnerability and interdependencies with critical infrastructure. Sustainability, 12. · DOI
  30. Abdulhamid, 2021, A survey of social media use in emergency situations: A literature review, Inf. Dev., 37, 274, 10.1177/0266666920913894 · DOI
  31. Liu, 2021, Organizational disaster communication ecology: Examining interagency coordination on social media during the onset of the COVID-19 pandemic, Am. Behav. Sci., 65, 914, 10.1177/0002764221992823 · DOI
  32. Aerts, 2018, Integrating human behaviour dynamics into flood disaster risk assessment, Nat. Clim. Change, 8, 193, 10.1038/s41558-018-0085-1 · DOI
  33. Walkling, 2020, Flood risk perceptions and coping capacities among the retired population, with implications for risk communication: A study of residents in a north Wales coastal town, UK, Int. J. Disaster Risk Reduct., 51, 101793, 10.1016/j.ijdrr.2020.101793 · DOI
  34. Osberghaus, D., Finkel, E., and Pohl, M. (2010). Individual Adaptation to Climate Change: The Role of Information and Perceived Risk, ZEW—Centre for European Economic Research. · DOI
  35. Maggi, 2016, Understanding urban mobility and the impact of public policies: The role of the agent-based models, Res. Transp. Econ., 55, 50, 10.1016/j.retrec.2016.04.010 · DOI
  36. Senanayake, 2024, Agent-based simulation for pedestrian evacuation: A systematic literature review, Int. J. Disaster Risk Reduct., 111, 104705, 10.1016/j.ijdrr.2024.104705 · DOI
  37. Shibuya, 2004, A framework of multi-agent-based modeling, simulation, and computational assistance in an ubiquitous environment, Simulation, 80, 367, 10.1177/0037549704046740 · DOI
  38. Serena, 2023, A review of multilevel modeling and simulation for human mobility and behavior, Simul. Model. Pract. Theory, 127, 102780, 10.1016/j.simpat.2023.102780 · DOI
  39. Tian, 2014, Use of an agent-based simulation model to evaluate a mobile-based system for supporting emergency evacuation decision making, J. Med. Syst., 38, 149, 10.1007/s10916-014-0149-3 · DOI
  40. Yi, 2007, A dynamic logistics coordination model for evacuation and support in disaster response activities, Eur. J. Oper. Res., 179, 1177, 10.1016/j.ejor.2005.03.077 · DOI
  41. Savage, 2019, Towards a complex model of disaster behaviour, Disasters, 43, 771, 10.1111/disa.12408 · DOI
  42. Haraguchi, 2022, Human mobility data and analysis for urban resilience: A systematic review, Environ. Plan. B Urban Anal. City Sci., 49, 1507, 10.1177/23998083221075634 · DOI
  43. Bellomo, 2016, Human behaviours in evacuation crowd dynamics: From modelling to “big data” toward crisis management, Phys. Life Rev., 18, 1, 10.1016/j.plrev.2016.05.014 · DOI
  44. Kim, 2018, Social network analysis: Characteristics of online social networks after a disaster, Int. J. Inf. Manag., 38, 86, 10.1016/j.ijinfomgt.2017.08.003 · DOI
  45. Li, 2017, Data-driven techniques in disaster information management, ACM Comput. Surv. (CSUR), 50, 1
  46. DeAngelis, D.L., and Diaz, S.G. (2019). Decision-making in agent-based modeling: A current review and future prospectus. Front. Ecol. Evol., 6. · DOI
  47. Du, 2017, Exploring the role of social media and individual behaviors in flood evacuation processes: An agent-based modeling approach, Water Resour. Res., 53, 9164, 10.1002/2017WR021192 · DOI
  48. Sakaguchi, 2015, Adaptive intermittent control: A computational model explaining motor intermittency observed in human behavior, Neural Netw., 67, 92, 10.1016/j.neunet.2015.03.012 · DOI
  49. Zhai, L., and Lee, J.E. (2023). Analyzing the disaster preparedness capability of local government using AHP: Zhengzhou 7.20 rainstorm disaster. Int. J. Environ. Res. Public Health, 20. · DOI
  50. Eloundou, T., Beutel, A., Robinson, D.G., Gu-Lemberg, K., Brakman, A.L., Mishkin, P., Shah, M., Heidecke, J., Weng, L., and Kalai, A.T. (2024). First-Person Fairness in Chatbots. arXiv.
  51. Kirchner, J.H., Chen, Y., Edwards, H., Leike, J., McAleese, N., and Burda, Y. (2024). Prover-Verifier Games improve legibility of LLM outputs. arXiv.
  52. Ye, Z., Agarwal, R., Liu, T., Joshi, R., Velury, S., Le, Q.V., Tan, Q., and Liu, Y. (2024). Evolving Alignment via Asymmetric Self-Play. arXiv.
  53. Ruoss, A., Delétang, G., Medapati, S., Grau-Moya, J., Wenliang, L.K., Catt, E., Reid, J., Lewis, C.A., Veness, J., and Genewein, T. (2024). Amortized Planning with Large-Scale Transformers: A Case Study on Chess. arXiv.
  54. Niu, Q., Liu, J., Bi, Z., Feng, P., Peng, B., Chen, K., Li, M., Yan, L.K., Zhang, Y., and Yin, C.H. (2024). Large Language Models and Cognitive Science: A Comprehensive Review of Similarities, Differences, and Challenges. arXiv.
  55. Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., and Zhou, E. (2023). The rise and potential of large language model based agents: A survey. arXiv.
  56. Zhang, Z., Rossi, R.A., Kveton, B., Shao, Y., Yang, D., Zamani, H., Dernoncourt, F., Barrow, J., Yu, T., and Kim, S. (2024). Personalization of Large Language Models: A Survey. arXiv.
  57. Kamruzzaman, M., and Kim, G.L. (2024). Prompting Techniques for Reducing Social Bias in LLMs through System 1 and System 2 Cognitive Processes. arXiv.
  58. Chu, Z., Chen, J., Chen, Q., Yu, W., He, T., Wang, H., Peng, W., Liu, M., Qin, B., and Liu, T. (2024). Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future. arXiv. · DOI
  59. Zhang, Y., Mao, S., Ge, T., Wang, X., de Wynter, A., Xia, Y., Wu, W., Song, T., Lan, M., and Wei, F. (2024). LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models. arXiv.
  60. Park, J.S., O’Brien, J., Cai, C.J., Morris, M.R., Liang, P., and Bernstein, M.S. (November, January 29). Generative agents: Interactive simulacra of human behavior. Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, San Francisco, CA, USA.
  61. Gürcan, Ö. (2024). LLM-Augmented Agent-Based Modelling for Social Simulations: Challenges and Opportunities. HHAI 2024: Hybrid Human AI Systems for the Social Good, IOS Press. · DOI
  62. Li, Y., Yu, Y., Li, H., Chen, Z., and Khashanah, K. (2023). TradingGPT: Multi-Agent System with Layered Memory and Distinct Characters for Enhanced Financial Trading Performance. arXiv.
  63. Merritt, 2024, The dynamics of social interaction among evolved model agents, Artif. Life, 30, 216, 10.1162/artl_a_00417 · DOI
  64. Wang, 2024, Load-aware continuous-time optimization for multi-agent systems: Toward dynamic resource allocation and real-time adaptability, Comput. Netw., 250, 110526, 10.1016/j.comnet.2024.110526 · DOI
  65. Leng, Y., and Yuan, Y. (2024). Do LLM Agents Exhibit Social Behavior?. arXiv.
  66. Guo, X., Huang, K., Liu, J., Fan, W., Vélez, N., Wu, Q., Wang, H., Griffiths, T.L., and Wang, M. (2024). Embodied LLM Agents Learn to Cooperate in Organized Teams. arXiv.
  67. Huang, J.-t., Lam, M.H., Li, E.J., Ren, S., Wang, W., Jiao, W., Tu, Z., and Lyu, M.R. (2024). Emotionally Numb or Empathetic? Evaluating How LLMs Feel Using EmotionBench. arXiv.
  68. Gao, 2024, Large language models empowered agent-based modeling and simulation: A survey and perspectives, Humanit. Soc. Sci. Commun., 11, 1259, 10.1057/s41599-024-03611-3 · DOI · Paper page
  69. Chiu, Y.Y., Sharma, A., Lin, I.W., and Althoff, T. (2024). A Computational Framework for Behavioral Assessment of LLM Therapists. arXiv.
  70. Yan, 2024, A computational framework for understanding firm communication during disasters, Inf. Syst. Res., 35, 590, 10.1287/isre.2022.0128 · DOI
  71. Ma, Q., Xue, X., Zhou, D., Yu, X., Liu, D., Zhang, X., Zhao, Z., Shen, Y., Ji, P., and Li, J. (2024). Computational Experiments Meet Large Language Model Based Agents: A Survey and Perspective. arXiv.
  72. Zhou, 2018, Emergency decision making for natural disasters: An overview, Int. J. Disaster Risk Reduct., 27, 567, 10.1016/j.ijdrr.2017.09.037 · DOI
  73. Sarker, 2021, Data science and analytics: An overview from data-driven smart computing, decision-making and applications perspective, SN Comput. Sci., 2, 377, 10.1007/s42979-021-00765-8 · DOI · Paper page
  74. Azzopardi, L. (2021, January 14–19). Cognitive biases in search: A review and reflection of cognitive biases in Information Retrieval. Proceedings of the ACM SIGIR Conference on Human Information Interaction and Retrieval, Canberra, ACT, Australia. · DOI
  75. Podolny, 1997, Resources and relationships: Social networks and mobility in the workplace, Am. Sociol. Rev., 62, 673, 10.2307/2657354 · DOI
  76. Shelke, 2019, Source detection of rumor in social network—A review, Online Soc. Netw. Media, 9, 30, 10.1016/j.osnem.2018.12.001 · DOI
  77. Oshio, 2018, Resilience and Big Five personality traits: A meta-analysis, Personal. Individ. Differ., 127, 54, 10.1016/j.paid.2018.01.048 · DOI
  78. Wachinger, 2013, The risk perception paradox—Implications for governance and communication of natural hazards, Risk Anal., 33, 1049, 10.1111/j.1539-6924.2012.01942.x · DOI
  79. Raikes, 2019, Pre-disaster planning and preparedness for floods and droughts: A systematic review, Int. J. Disaster Risk Reduct., 38, 101207, 10.1016/j.ijdrr.2019.101207 · DOI
  80. Lai, 2021, Trajectories of Posttraumatic Stress in Youths After Natural Disasters, JAMA Netw. Open, 4, e2036682, 10.1001/jamanetworkopen.2020.36682 · DOI
  81. Sutton, 2014, Warning tweets: Serial transmission of messages during the warning phase of a disaster event, Inf. Commun. Soc., 17, 765, 10.1080/1369118X.2013.862561 · DOI
  82. Hayles, 2010, An examination of decision making in post disaster housing reconstruction, Int. J. Disaster Resil. Built Environ., 1, 103, 10.1108/17595901011026508 · DOI

Cited by

Sorted by citations

Metadata

Authors
Zhao, X., Wang, H., Dai, C., Tang, J., Deng, K., Zhong, Z., Kong, F., Wang, S., & Morikawa, S.
Affiliations
  • The University of Tokyo (JP)
  • China Agricultural University (CN)
  • Universiti Tunku Abdul Rahman (MY)
  • Shandong Normal University (CN)
  • Chengdu University of Technology (CN)
  • Institute of Science Tokyo (JP)
  • Northeast Forestry University (CN)
  • University of Copenhagen (DK)
Corresponding author
  • Wang, Hao
  • Morikawa, So
ORCID
Venue
Systems
Publisher
MDPI AG
Published
2025-03-31
Volume
13
Issue
4
Pages
240
ISSN
2079-8954 (ISSN-L)
DOI
10.3390/systems13040240
OpenAlex
W4409010281
Cited by
10
References
7
Citations by year
2026: 10
FWCI
9.72
Type
journal article
Language
en
Open access
Licence
Locations
  • Systems (publishedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
Youth Project of the National Social Science Foundation of China (20CSH089)
Topics
  • Social Sciences › Sociology and Political Science › Disaster Management and Resilience
  • Social Sciences › Safety Research › Evacuation and Crowd Dynamics
  • Social Sciences › Sociology and Political Science › Risk Perception and Management
Keywords
disaster risk perception, disaster decision-making, large language models, social influence, demographic factors, ecological validity, disaster policy

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review