Predicting Psychological Distress Amid the COVID-19 Pandemic by Machine Learning: Discrimination and Coping Mechanisms of Korean Immigrants in the U.S.

Predicting Psychological Distress Amid the COVID-19 Pandemic by Machine Learning: Discrimination and Coping Mechanisms of Korean Immigrants in the U.S.

Shinwoo Choi, Joo Young Hong, Yong Je Kim, Hyejoon Park

The current study examined the predictive ability of discrimination-related variables, coping mechanisms, and sociodemographic factors on the psychological distress level of Korean immigrants in the U.S. amid the COVID-19 pandemic. Korean immigrants (both foreign-born and U.S.-born) in the U.S. above the age of 18 were invited to participate in an online survey through purposive sampling. In order to verify the variables predicting the level of psychological distress on the final sample from 42 states (n = 790), the Artificial Neural Network (ANN) analysis, which is able to examine complex non-linear interactions among variables, was conducted. The most critical predicting variables in the neural network were a person’s resilience, experiences of everyday discrimination, and perception that racial discrimination toward Asians has increased in the U.S. since the beginning of the COVID-19 pandemic.

2020

United States, mental health, covid-19, racism, Artificial neural network, Korean immigrants

10.3390/ijerph17176057

Epidemiology and Health

Korean Society of Epidemiology

Medicine