Predicting fear and perceived health during the COVID-19 pandemic using machine learning: A cross-national longitudinal study

• DOI: 10.1371/journal.pone.0247997
• Publication Date: 2021-03-11T18:46:47Z
• Authors: Stephanie Josephi...; David Steyrl; Michal Mikolaj St...; Michał Pieniak; Judit Martínez Mo...; Ondra Pešout; Jakub Binter; Patrick Smela; Frank Scharnowski; Andrew A. Nicholson
• Keywords: Pandemic; Vulnerability; Longitudinal Study

During medical pandemics, protective behaviors need to be motivated by effective communication, where finding predictors of fear and perceived health is critical importance. The varying trajectories the COVID-19 pandemic in different countries afford opportunity assess unique influence 'macro-level' environmental factors 'micro-level' psychological variables on both health. Here, we investigate using machine learning as lockdown restrictions response were introduced Austria, Spain, Poland Czech Republic. Over a seven-week period, 533 participants completed weekly self-report surveys which measured target subjective virus health, addition potential predictive related factors, social vulnerability disease (PVD), economic circumstances. Viral spread, mortality governmental responses further included analysis predictors. Results revealed that our models could accurately predict (accounting for approximately 23% variance) such worrying about shortages food supplies interestingly, spread did not contribute this prediction. Furthermore, results predicted PVD, physical exercise, attachment anxiety age input features, albeit with smaller effect sizes. Taken together, emphasize importance opposed when predicting offer starting point more extensive research influences pathogen threat psychology