Predicting attitudinal and behavioral responses to COVID-19 pandemic using machine learning.
Pavlović T., Azevedo F., De K., Riaño-Moreno JC., Maglić M., Gkinopoulos T., Donnelly-Kehoe PA., Payán-Gómez C., Huang G., Kantorowicz J., Birtel MD., Schönegger P., Capraro V., Santamaría-García H., Yucel M., Ibanez A., Rathje S., Wetter E., Stanojević D., van Prooijen J-W., Hesse E., Elbaek CT., Franc R., Pavlović Z., Mitkidis P., Cichocka A., Gelfand M., Alfano M., Ross RM., Sjåstad H., Nezlek JB., Cislak A., Lockwood P., Abts K., Agadullina E., Amodio DM., Apps MAJ., Aruta JJB., Besharati S., Bor A., Choma B., Cunningham W., Ejaz W., Farmer H., Findor A., Gjoneska B., Gualda E., Huynh TLD., Imran MA., Israelashvili J., Kantorowicz-Reznichenko E., Krouwel A., Kutiyski Y., Laakasuo M., Lamm C., Levy J., Leygue C., Lin M-J., Mansoor MS., Marie A., Mayiwar L., Mazepus H., McHugh C., Olsson A., Otterbring T., Packer D., Palomäki J., Perry A., Petersen MB., Puthillam A., Rothmund T., Schmid PC., Stadelmann D., Stoica A., Stoyanov D., Stoyanova K., Tewari S., Todosijević B., Torgler B., Tsakiris M., Tung HH., Umbreș RG., Vanags E., Vlasceanu M., Vonasch AJ., Zhang Y., Abad M., Adler E., Mdarhri HA., Antazo B., Ay FC., Ba MEH., Barbosa S., Bastian B., Berg A., Białek M., Bilancini E., Bogatyreva N., Boncinelli L., Booth JE., Borau S., Buchel O., de Carvalho CF., Celadin T., Cerami C., Chalise HN., Cheng X., Cian L., Cockcroft K., Conway J., Córdoba-Delgado MA., Crespi C., Crouzevialle M., Cutler J., Cypryańska M., Dabrowska J., Davis VH., Minda JP., Dayley PN., Delouvée S., Denkovski O., Dezecache G., Dhaliwal NA., Diato A., Di Paolo R., Dulleck U., Ekmanis J., Etienne TW., Farhana HH., Farkhari F., Fidanovski K., Flew T., Fraser S., Frempong RB., Fugelsang J., Gale J., García-Navarro EB., Garladinne P., Gray K., Griffin SM., Gronfeldt B., Gruber J., Halperin E., Herzon V., Hruška M., Hudecek MFC., Isler O., Jangard S., Jørgensen F., Keudel O., Koppel L., Koverola M., Kunnari A., Leota J., Lermer E., Li C., Longoni C., McCashin D., Mikloušić I., Molina-Paredes J., Monroy-Fonseca C., Morales-Marente E., Moreau D., Muda R., Myer A., Nash K., Nitschke JP., Nurse MS., de Mello VO., Palacios-Galvez MS., Pan Y., Papp Z., Pärnamets P., Paruzel-Czachura M., Perander S., Pitman M., Raza A., Rêgo GG., Robertson C., Rodríguez-Pascual I., Saikkonen T., Salvador-Ginez O., Sampaio WM., Santi GC., Schultner D., Schutte E., Scott A., Skali A., Stefaniak A., Sternisko A., Strickland B., Thomas JP., Tinghög G., Traast IJ., Tucciarelli R., Tyrala M., Ungson ND., Uysal MS., Van Rooy D., Västfjäll D., Vieira JB., von Sikorski C., Walker AC., Watermeyer J., Willardt R., Wohl MJA., Wójcik AD., Wu K., Yamada Y., Yilmaz O., Yogeeswaran K., Ziemer C-T., Zwaan RA., Boggio PS., Whillans A., Van Lange PAM., Prasad R., Onderco M., O'Madagain C., Nesh-Nash T., Laguna OM., Kubin E., Gümren M., Fenwick A., Ertan AS., Bernstein MJ., Amara H., Van Bavel JJ.
At the beginning of 2020, COVID-19 became a global problem. Despite all the efforts to emphasize the relevance of preventive measures, not everyone adhered to them. Thus, learning more about the characteristics determining attitudinal and behavioral responses to the pandemic is crucial to improving future interventions. In this study, we applied machine learning on the multinational data collected by the International Collaboration on the Social and Moral Psychology of COVID-19 (N = 51,404) to test the predictive efficacy of constructs from social, moral, cognitive, and personality psychology, as well as socio-demographic factors, in the attitudinal and behavioral responses to the pandemic. The results point to several valuable insights. Internalized moral identity provided the most consistent predictive contribution-individuals perceiving moral traits as central to their self-concept reported higher adherence to preventive measures. Similar results were found for morality as cooperation, symbolized moral identity, self-control, open-mindedness, and collective narcissism, while the inverse relationship was evident for the endorsement of conspiracy theories. However, we also found a non-neglible variability in the explained variance and predictive contributions with respect to macro-level factors such as the pandemic stage or cultural region. Overall, the results underscore the importance of morality-related and contextual factors in understanding adherence to public health recommendations during the pandemic.