[en] Using a unique harmonized real‐time data set from the COME‑HERE longitudinal survey that covers five European countries (France, Germany, Italy, Spain, and Sweden) and applying a non‑parametric machine learning model, this paper identifies the main individual and macro‑level predictors of self‑protecting behaviors against the coronavirus disease 2019 (COVID‑19) during the first wave of the pandemic. Exploiting the interpretability of a Random Forest algorithm via Shapely values, we find that a higher regional incidence of COVID‑19 triggers higher levels of self‑protective behavior, as does a stricter government policy response. The level of individual knowledge about the pandemic, confidence in institutions, and population density also ranks high among the factors that predict self‑protecting behaviors. We also identify a steep socioeconomic gradient with lower levels of self‑protecting behaviors being associated with lower income and poor housing conditions. Among socio‑demographic factors, gender, marital status, age, and region of residence are the main determinants of self‑protective measures.
Disciplines :
Sciences de la santé humaine: Multidisciplinaire, généralités & autres
GREIFF, Samuel ; University of Luxembourg > Faculty of Humanities, Education and Social Sciences (FHSE) > Department of Behavioural and Cognitive Sciences (DBCS)
Vögele, Claus ; University of Luxembourg > Faculty of Humanities, Education and Social Sciences (FHSE) > Department of Behavioural and Cognitive Sciences (DBCS)
d'Ambrosio, Conchita ; University of Luxembourg > Faculty of Humanities, Education and Social Sciences (FHSE) > Department of Behavioural and Cognitive Sciences (DBCS)
Co-auteurs externes :
no
Langue du document :
Anglais
Titre :
A machine learning approach to predict self‑protecting behaviors during the early wave of the COVID‑19 pandemic
Dergaa, I. et al. Organising football matches with spectators during the COVID-19 pandemic: What can we learn from the Amir Cup Football Final of Qatar 2020? A call for action. Biol. Sport 38, 677–681 (2021).
Musa, S., Elyamani, R. & Dergaa, I. COVID-19 and screen-based sedentary behaviour: Systematic review of digital screen time and metabolic syndrome in adolescents. PLoS ONE 17, e0265560 (2022).
Trabelsi, K. et al. Globally altered sleep patterns and physical activity levels by confinement in 5056 individuals: ECLB COVID-19 international online survey. Biol. Sport 38, 495–506 (2021).
Hale, T. et al. A global panel database of pandemic policies (Oxford COVID-19 Government Response Tracker). Nat. Hum. Behav. 5, 529–538 (2021).
Aubert, C. & Augeraud-Véron, E. The relative power of individual distancing efforts and public policies to curb the COVID-19 epidemics. PLoS ONE 16, e0250764 (2021).
Brown, C. S., Ravallion, M. Inequality and the Coronavirus: Socioeconomic Covariates of Behavioral Responses and Viral Outcomes Across US Counties. (National Bureau of Economic Research WP 27549, 2020).
Papageorge, N. W. et al. Socio-demographic factors associated with self-protecting behavior during the Covid-19 pandemic. J. Popul. Econ. 34, 691–738 (2021).
Ashraf, B. N. Economic impact of government interventions during the COVID-19 pandemic: International evidence from financial markets. J. Behav. Exp. Financ. 27, 100371 (2020).
Adda, J. Economic activity and the spread of viral diseases: Evidence from high frequency data. Q. J. Econ. 131(2), 891–941 (2016).
Cutler, D. M. & Lleras-Muney, A. Understanding differences in health behaviors by education. J. Health Econ. 29, 1–28 (2010).
Pampel, F. C., Krueger, P. M. & Denney, J. T. Socioeconomic disparities in health behaviors. Ann. Rev. Sociol. 36, 349–370 (2010).
Wright, A. L., Sonin, K., Driscoll, J. & Wilson, J. Poverty and economic dislocation reduce compliance with COVID-19 shelter-in-place protocols. J. Econ. Behav. Organ. 180, 544–554 (2020).
Chiou, L., & Tucker, C. Social Distancing, Internet Access and Inequality. (National Bureau of Economic Research WP 26982, 2020).
Barrios, J. M., & Hochberg, Y. Risk Perception Through the Lens of Politics in the Time of the COVID-19 Pandemic. (National Bureau of Economic Research WP 27008, 2020).
Painter, M. & Qiu, T. Political beliefs affect compliance with covid-19 social distancing orders. Covid Econ. 4, 103–123 (2020).
Simonov, A., Sacher, S. K., Dubé, J.-P. H., & Biswas, S. The Persuasive Effect of Fox News: Non-Compliance with Social Distancing During the COVID-19 Pandemic. (National Bureau of Economic Research WP 27237, 2020).
Abel, M., Byker, T. & Carpenter, J. Socially optimal mistakes? Debiasing COVID-19 mortality risk perceptions and prosocial behavior. J. Econ. Behav. Organ. 183, 456–480 (2021).
Jadil, Y. & Ouzir, M. Exploring the predictors of health-protective behavior during the COVID-19 pandemic: A multi-country comparison. Environ. Res. 199, 111376 (2021).
Vacondio, M., Priolo, G., Dickert, S. & Bonini, N. Worry, perceived threat and media communication as predictors of self-protective behaviors during the COVID-19 outbreak in Europe. Front. Psychol. 12, 231 (2021).
Jørgensen, F., Bor, A. & Petersen, M. B. Compliance without fear: Individual-level protective behaviour during the first wave of the COVID-19 pandemic. Br. J. Health Psychol. 26, 679–696 (2021).
Dohle, S., Wingen, T. & Schreiber, M. Acceptance and adoption of protective measures during the COVID-19 pandemic: The role of trust in politics and trust in science. Soc. Psychol. Bull. 15, 1–23 (2020).
Lep, Ž, Babnik, K. & Beyazoglu, K. H. The role of information credibility in emotional responses and engagement in self-protective behaviour within days of the COVID-19 outbreak: A cross-sectional study. Front. Psychol. 11, 1846 (2020).
Athey, S. The impact of machine learning on economics. in The Economics of Artificial Intelligence. 507–552. (University of Chicago Press, 2019).
Athey, S. & Imbens, G. Recursive partitioning for heterogeneous causal effects. Proc. Natl. Acad. Sci. 113, 7353–7360 (2016).
Grimmer, J., Messing, S. & Westwood, S. J. Estimating heterogeneous treatment effects and the effects of heterogeneous treatments with ensemble methods. Polit. Anal. 25, 413–434 (2017).
Imai, K. & Ratkovic, M. Estimating treatment effect heterogeneity in randomized program evaluation. Ann. Appl. Stat. 7, 443–470 (2013).
Künzel, S. R., Sekhon, J. S., Bickel, P. J. & Yu, B. Metalearners for estimating heterogeneous treatment effects using machine learning. Proc. Natl. Acad. Sci. 116, 4156–4165 (2019).
Wager, S. & Athey, S. Estimation and inference of heterogeneous treatment effects using random forests. J. Am. Stat. Assoc. 113, 1228–1242 (2018).
Van Lissa, C. J., Stroebe, W., Leander, P., Agostini, M., Gutzkow, B., Kreienkamp, J., Belanger, J., Draws, T., Grygoryshyn, A., & Vetter, C. S. Early Indicators of COVID-19 Infection Prevention Behaviors: Machine Learning Identifies Personal and Country-Level Factors. PsyArXiv Preprints 5 Nov 2020 (2020).
Eder, S. J. et al. Predicting fear and perceived health during the COVID-19 pandemic using machine learning: A cross-national longitudinal study. PLoS ONE 16, e0247997 (2021).
Prout, T. A. et al. Identifying predictors of psychological distress during COVID-19: A machine learning approach. Front. Psychol. 11, 3063 (2020).
Angrist, J. D. & Pischke, J.-S. Mostly Harmless Econometrics: An Empiricist’s Companion (Princeton University Press, 2009).
Shmueli, G. To explain or to predict?. Stat. Sci. 25, 289–310 (2010).
Vögele, C., Lutz, A., Yin, R., & D’Ambrosio, C. How do different confinement measures affect people in Luxembourg, France, Germany, Italy, Spain and Sweden? in COME‐HERE: First Report. Luxembourg. https://Wwwen.Uni.Lu/Research/Highlights/How_do_diffErent_confinement_measures_affect_people_first_reSults. Accessed 7 July 2020. (2020).
Grinsztajn, L., Oyallon, E., & Varoquaux, G. Why Do Tree-Based Models Still Outperform Deep Learning on Tabular Data? arXiv preprint arXiv:2207.08815 (2022).
Pedregosa, F. et al. Scikit-learn: Machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011).
Lundberg, S. M., & Lee, S.-I. A unified approach to interpreting model predictions. in Proceedings of the 31st International Conference on Neural Information Processing Systems. 4768–4777 (2017).
Shapley, L. A Value for n-person games, contributions to the theory of games (Kuhn, H.W., Tucker, A.W. Eds.). 307–317. Ann. Math. Stud. 28, 275–293 (1953).
Guidotti, R. et al. A survey of methods for explaining black box models. ACM Comput. Surv. (CSUR) 51, 1–42 (2018).
Molnar, C. Interpretable Machine Learning. Lulu.com (2020).
Kassa, S. M. & Ouhinou, A. Epidemiological models with prevalence dependent endogenous self-protection measure. Math. Biosci. 229, 41–49 (2011).
Yang, Y. & Xiang, X. Examine the associations between perceived neighborhood conditions, physical activity, and mental health during the COVID-19 pandemic. Health Place 67, 102505 (2021).
Dietz, W. & Santos-Burgoa, C. Obesity and its implications for COVID-19 mortality. Obesity 28, 1005 (2020).
Mendoza-Jiménez, M.-J., Hannemann, T.-V. & Atzendorf, J. Behavioral risk factors and adherence to preventive measures: Evidence from the early stages of the COVID-19 pandemic. Front. Public Health 9, 674597 (2021).
McLaren, L. Socioeconomic status and obesity. Epidemiol. Rev. 29, 29–48 (2007).
Dai, M. et al. Influence of cigarettes and alcohol on the severity and death of COVID-19: A multicenter retrospective study in Wuhan, China. Front. Physiol. 11, 588553 (2020).
Reddy, R. K. et al. The effect of smoking on COVID-19 severity: A systematic review and meta-analysis. J. Med. Virol. 93, 1045–1056 (2021).
Niedzwiedz, C. L. et al. Ethnic and socioeconomic differences in SARS-CoV-2 infection: Prospective cohort study using UK Biobank. BMC Med. 18, 1–14 (2020).
Alsharawy, A., Spoon, R., Smith, A. & Ball, S. Gender differences in fear and risk perception during the COVID-19 pandemic. Front. Psychol. 12, 3104 (2021).
Alon, T., Doepke, M., Olmstead-Rumsey, J., & Tertilt, M. The Impact of COVID-19 on Gender Equality. (National Bureau of Economic Research WP 26947, 2020).
Biroli, P. et al. Family life in lockdown. Front. Psychol. 12, 697570 (2021).
Collins, C., Landivar, L. C., Ruppanner, L. & Scarborough, W. J. COVID-19 and the gender gap in work hours. Gend. Work. Organ. 28, 101–112 (2021).
Xue, B. & McMunn, A. Gender differences in unpaid care work and psychological distress in the UK Covid-19 lockdown. PLoS ONE 16, e0247959 (2021).
Stickley, A., Matsubayashi, T. & Ueda, M. Loneliness and COVID-19 preventive behaviours among Japanese adults. J. Public Health 43, 53–60 (2021).
