Positive relationship between education level and risk perception and behavioral response: A machine learning approach

PLOS ONE | https://doi.org/10.1371/journal.pone.0321153 April 3, 2025 1 / 10 OPEN ACCESS Citation: Wei Z, Zhang Z, Guo L, Zhou W, Yang K (2025) Positive relationship between education level and risk perception and behavioral response: A machine learning approach. PLoS ONE 20(4): e0321153. https:// doi.org/10.1371/journal.pone.0321153 Editor: Yasuko Kawahata, Rikkyo University: Rikkyo Daigaku, JAPAN Received: December 19, 2024 Accepted: March 3, 2025 Published: April 3, 2025 Copyright: © 2025 Wei et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Data availability statement: All relevant data are within the manuscript and its Supporting Information file. Funding: The author(s) received no specific funding for this work. Competing interests: The authors have declared that no competing interests exist. RESEARCH ARTICLE Positive relationship between education level and risk perception and behavioral response: A machine learning approach Zhipeng Wei1,2,3, Zhichun Zhang1,2,3, Liping Guo1,2,3, Wenjie Zhou2,3,4, Kehu Yang 1,2,3* 1 Evidence-based Medicine Center, School of Basic Medical Sciences, Lanzhou University, Lanzhou, China, 2 Center for Evidence-based Social Science, School of Public Health, Lanzhou University, Lanzhou, China, 3 Innovation Laboratory of Evidence-based Social Science, Lanzhou University, Lanzhou,

China, 4 School of Information Resource Management, Renmin University of China, Beijing, China * yangkh-ebm@lzu.edu.cn Abstract This paper aims to examine the influence mechanism of education level as a key situa- tional factor in the relationship between risk perception and behavioral response, encom- passing both behavioral intention and preparatory behavior. Utilizing non-parametric estimation techniques in machine learning, particularly the Random Forest and XGBoost algorithms, this study develops predictive models to analyze the impact of 27 influenc- ing factors on behavioral responses following risk perception. The findings indicate that, while the model’s fit for preparatory behavior is 25.71% and its fit for behavioral intention is below 20%, the model effectively identifies key influencing factors. Further analysis employing SHAP values demonstrates that education level not only exerts a significant influence but also exhibits varying effects across different educational groups. More- over, statistical testing corroborates the importance of education level in the relationship between risk perception and behavioral response, providing a robust scientific foundation for the development of risk management policies. 1. Introduction Risk perception and behavioral response are vital elements of decision-making under uncer- tainty, especially in situations such as natural disasters, public health emergencies, and environmental threats. It’s crucial to understand the mechanisms that affect these processes to

create effective risks management strategies. Among the numerous factors that influence risk perception and behavioral response, education level has been identified as a significant con- textual variable. Nevertheless, the specific mechanisms by which education level impacts these outcomes are still not well understood, particularly in complex real-world situations where multiple variables interact in dynamic ways. Risk perception has long been a central focus in disaster management and behavioral science. According to Siegrist and Arvai [1], research on risk perception can be broadly clas- sified into three primary approaches: the characteristics of hazards, the characteristics of risk perceivers, and the application of heuristics in risk judgments.