Contextual factors predicting compliance behavior during the COVID-19 pandemic: A machine learning analysis on survey data from 16 countries

PLoS One. 2022 Nov 28;17(11):e0276970. doi: 10.1371/journal.pone.0276970. eCollection 2022.

Abstract

Voluntary isolation is one of the most effective methods for individuals to help prevent the transmission of diseases such as COVID-19. Understanding why people leave their homes when advised not to do so and identifying what contextual factors predict this non-compliant behavior is essential for policymakers and public health officials. To provide insight on these factors, we collected data from 42,169 individuals across 16 countries. Participants responded to items inquiring about their socio-cultural environment, such as the adherence of fellow citizens, as well as their mental states, such as their level of loneliness and boredom. We trained random forest models to predict whether someone had left their home during a one week period during which they were asked to voluntarily isolate themselves. The analyses indicated that overall, an increase in the feeling of being caged leads to an increased probability of leaving home. In addition, an increased feeling of responsibility and an increased fear of getting infected decreased the probability of leaving home. The models predicted compliance behavior with between 54% and 91% accuracy within each country's sample. In addition, we modeled factors leading to risky behavior in the pandemic context. We observed an increased probability of visiting risky places as both the anticipated number of people and the importance of the activity increased. Conversely, the probability of visiting risky places increased as the perceived putative effectiveness of social distancing decreased. The variance explained in our models predicting risk ranged from < .01 to .54 by country. Together, our findings can inform behavioral interventions to increase adherence to lockdown recommendations in pandemic conditions.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • COVID-19* / epidemiology
  • COVID-19* / prevention & control
  • Communicable Disease Control
  • Humans
  • Machine Learning
  • Pandemics
  • Physical Distancing

Grants and funding

Balazs Aczel, Nandor Hajdu and Barnabas Szaszi were supported by the Hungarian National Research, Development and Innovation Office (NKFIH-1157-8/2019-DT); Gabriel Baník was supported by APVV-17-0418; Patrícia Arriaga was supported by the Portuguese National Funding Agency for Science and Technology (FCT, REF UID/PSI/03125/2020).; Ivan Ropovik was supported by PRIMUS/20/HUM/009; Matus Adamkovic was supported by the Slovak Research and Development Agency [project no. APVV-20-0319]; Dmitry Grigoryev and Dmitrii Dubrov were supported by the HSE University Basic Research Program; Krystian Barzykowski and Ewa Ilczuk were supported by the National Science Centre, Poland (UMO-2019/35/B/HS6/00528). The research reported in this paper is part of project no. BME-NVA-02, implemented with the support provided by the Ministry of Innovation and Technology of Hungary from the National Research, Development and Innovation Fund, financed under the TKP2021 funding scheme. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.