Using machine learning to identify important predictors of COVID-19 infection prevention behaviors during the early phase of the pandemic

Van Lissa, Caspar J. and Stroebe, Wolfgang and vanDellen, Michelle R. and Leander, N. Pontus and Agostini, Maximilian and Draws, Tim and Grygoryshyn, Andrii and Gützgow, Ben and Kreienkamp, Jannis and Vetter, Clara S. and Abakoumkin, Georgios and Abdul Khaiyom, Jamilah Hanum and Ahmedi, Vjolica and Akkas, Handan and Almenara, Carlos A. and Atta, Mohsin and Bağcı, Çiğdem and Basel, Sima and Kida, Edona Berisha and Bernardo, Allan B.I. and Buttrick, Nicholas R. and Chobthamkit, Phatthanakit and Choi, Hoon Seok and Cristea, Mioara and Csaba, Sára and Damnjanović, Kaja and Danyliuk, Ivan and Dash, Arobindu and Di Santo, Daniela and Douglas, Karen M. and Enea, Violeta and Faller, Daiane Gracieli and Fitzsimons, Gavan J. and Gheorghiu, Alexandra and Gómez, Ángel and Hamaidia, Ali and Han, Qing and Helmy, Mai and Hudiyana, Joevarian and Jeronimus, Bertus F. and Jiang, Ding Yu and Jovanović, Veljko and Kamenov, Željka and Kende, Anna and Keng, Shian Ling and Thanh Kieu, Tra Thi and Koc, Yasin and Kovyazina, Kamila and Kozytska, Inna and Krause, Joshua and Kruglanksi, Arie W. and Kurapov, Anton and Kutlaca, Maja and Lantos, Nóra Anna and Lemay, Edward P. and Jaya Lesmana, Cokorda Bagus and Louis, Winnifred R. and Lueders, Adrian and Malik, Najma Iqbal and Martinez, Anton P. and McCabe, Kira O. and Mehulić, Jasmina and Milla, Mirra Noor and Mohammed, Idris and Molinario, Erica and Moyano, Manuel and Muhammad, Hayat and Mula, Silvana and Muluk, Hamdi and Myroniuk, Solomiia and Najafi, Reza and Nisa, Claudia F. and Nyúl, Boglárka and O'Keefe, Paul A. and Olivas Osuna, Jose Javier and Osin, Evgeny N. and Park, Joonha and Pica, Gennaro and Pierro, Antonio and Rees, Jonas H. and Reitsema, Anne Margit and Resta, Elena and Rullo, Marika and Ryan, Michelle K. and Samekin, Adil and Santtila, Pekka and Sasin, Edyta M. and Schumpe, Birga M. and Selim, Heyla A. and Stanton, Michael Vicente and Sultana, Samiah and Sutton, Robbie M. and Tseliou, Eleftheria and Utsugi, Akira and Anne van Breen, Jolien and Van Veen, Kees and Vázquez, Alexandra and Wollast, Robin and Wai-Lan Yeung, Victoria and Zand, Somayeh and Žeželj, Iris Lav and Zheng, Bang and Zick, Andreas and Zúñiga, Claudia and Bélanger, Jocelyn J. (2022) Using machine learning to identify important predictors of COVID-19 infection prevention behaviors during the early phase of the pandemic. Patterns, 3 (4). ISSN 2666-3899

Full text not available from this repository. (Request a copy)

Abstract

Before vaccines for coronavirus disease 2019 (COVID-19) became available, a set of infection-prevention behaviors constituted the primary means to mitigate the virus spread. Our study aimed to identify important predictors of this set of behaviors. Whereas social and health psychological theories suggest a limited set of predictors, machine-learning analyses can identify correlates from a larger pool of candidate predictors. We used random forests to rank 115 candidate correlates of infection-prevention behavior in 56,072 participants across 28 countries, administered in March to May 2020. The machine-learning model predicted 52% of the variance in infection-prevention behavior in a separate test sample—exceeding the performance of psychological models of health behavior. Results indicated the two most important predictors related to individual-level injunctive norms. Illustrating how data-driven methods can complement theory, some of the most important predictors were not derived from theories of health behavior—and some theoretically derived predictors were relatively unimportant.
Item Type: Article
Uncontrolled Keywords: COVID-19; DSML2: Proof-of-concept: Data science output has been formulated, implemented, and tested for one domain/problem; health behaviors; machine learning; public goods dilemma; random forest; social norms
Divisions: Faculty of Arts and Social Sciences
Depositing User: Çiğdem Bağcı
Date Deposited: 23 Aug 2022 11:13
Last Modified: 23 Aug 2022 11:13
URI: https://research.sabanciuniv.edu/id/eprint/44106

Actions (login required)

View Item
View Item