[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127553-en":3,"doc-seo-127553-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},127553,687207020761,"Patrick","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Predicting COVID-19 exposure risk perception using machine learning","Self-perceived exposure risk strongly influences compliance with COVID-19 preventive measures and is a key predictor of mental health problems. A study based on survey data from 5,001 Norwegians (2020–2021) uses interpretable machine learning to forecast perceived exposure risk and identify major predictors. Gradient boosting provides the best performance, while Shapley values assess individual heterogeneity and feature interactions. Results highlight socially patterned determinants across pandemic phases, informing timely, group-tailored interventions and early identification of vulnerable people.","Bakkeli BMC Public Health (2023) 23:1377 [https://doi.org/10.1186/s12889-023-16236-z](https://doi.org/10.1186/s12889-023-16236-z)  \nBMC Public Health  \n RESEARCH Open Access  \nPredicting COVID-19 exposure risk perception using machine learning  \nNan Zou Bakkeli 1*  \nAbstract  \nBackground Self-perceived exposure risk determines the likelihood of COVID-19 preventive measure compliance to a large extent and is among the most important predictors of mental health problems. Therefore, there is a need to systematically identify important predictors of such risks. This study aims to provide insight into forecasting and understanding risk perceptions and help to adjust interventions that target various social groups in different pandemic phases.  \nMethods This study was based on survey data collected from 5001 Norwegians in 2020 and 2021. Interpretable machine learning algorithms were used to predict perceived exposure risks. To detect the most important predictors, the models with best performance were chosen based on predictive errors and explained variances. Shapley additive values were used to examine individual heterogeneities, interpret feature impact and check interactions between the key predictors.  \nResults Gradient boosting machine exhibited the best model performance in this study (2020: RMSE= . 93, MAE= . 74, RSQ= . 22; 2021: RMSE= . 99, MAE= . 77, RSQ= . 12) . The most influential predictors of perceived exposure risk were compliance with interventions, work-life conflict, age and gender. In 2020, work and occupation played a dominant role in predicting perceived risks whereas, in 2021, living and behavioural factors were among the most important predictors. Findings show large individual heterogeneities in feature importance based on people’s sociodemographic backgrounds, work and living situations.  \nConclusion The findings provide insight into forecasting risk groups and contribute to the early detection of vulnerable people during the pandemic. This is useful for policymakers and stakeholders in developing timely interventions targeting different social groups. Future policies and interventions should be adapted to the needs of people with various life situations.  \nKeywords Exposure risks, Risk perception, COVID-19, Health inequality, Social determinants of health, Occupational health, Interpretable machine learning  \n*Correspondence: Nan Zou Bakkeli [Nan.Bakkeli@OsloMet. no](Nan.Bakkeli@OsloMet. no)  \n1 Centre for Research on Pandemics & Society; Consumption Research Norway, Oslo Metropolitan University, P. O. Box 4, St Olavs Plass, Oslo 0130, Norway  \nIntroduction  \nThe COVID-19 pandemic has posed considerable challenges in people’s daily lives. Although pandemics are random in nature, each individual’s vulnerability to exposure is unequally distributed. Studies have found that people with lower socioeconomic status, precarious employment and poor living conditions are more exposed and face larger health challenges than others [1–3]. Exposure to COVID-19 not only impacts people’s physical health, but is also a risk factor for mental  \n© The Author(s) 2023. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit [http://creativecommons.org/licenses/by/4.0/](http://creativecommons","cbCaipyGLULyZjWr","https://ap.wps.com/l/cbCaipyGLULyZjWr","pdf",3325031,1,19,"English","en",105,"# Abstract\n# Methods\n# Results\n## Model performance\n## Key predictors and heterogeneity\n# Conclusion\n# Keywords","[{\"question\":\"What is the study’s main goal regarding COVID-19 exposure risk perception?\",\"answer\":\"To forecast and explain how people form perceived exposure risk, and to identify important predictors that can guide interventions for different social groups across pandemic phases.\"},{\"question\":\"Which data and modeling approach are used?\",\"answer\":\"The study uses survey data from 5,001 Norwegians collected in 2020 and 2021, applying interpretable machine learning models and selecting the best-performing models by predictive error and explained variance.\"},{\"question\":\"How are individual differences and feature contributions analyzed?\",\"answer\":\"Shapley additive values are used to examine individual heterogeneities, interpret the impact of features, and test interactions between key predictors.\"}]","Predicting COVID-19 exposure risk perception using machine learning | PDF",1785939925,48,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"predicting-covid-19-exposure-risk-perception-using-machine-learning","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/predicting-covid-19-exposure-risk-perception-using-machine-learning/127553/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-22","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What is the study’s main goal regarding COVID-19 exposure risk perception?","Question",{"text":76,"@type":77},"To forecast and explain how people form perceived exposure risk, and to identify important predictors that can guide interventions for different social groups across pandemic phases.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Which data and modeling approach are used?",{"text":81,"@type":77},"The study uses survey data from 5,001 Norwegians collected in 2020 and 2021, applying interpretable machine learning models and selecting the best-performing models by predictive error and explained variance.",{"name":83,"@type":74,"acceptedAnswer":84},"How are individual differences and feature contributions analyzed?",{"text":85,"@type":77},"Shapley additive values are used to examine individual heterogeneities, interpret the impact of features, and test interactions between key predictors.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":107,"slug":138},"General","general"]