摘要：During the COVID-19 pandemic, every day, updated case numbers and the lasting time of the pandemic became major concerns of people. We collected the online data (28 January to 7 March 2020 during the COVID-19 outbreak) of 16,453 social media users living in mainland China. Computerized machine learning models were developed to estimate their daily scores of the nine dimensions of the Symptom Checklist—90 (SCL-90). Repeated measures analysis of variance (ANOVA) was used to compare the SCL-90 dimension scores between Wuhan and non-Wuhan residents. Fixed effect models were used to analyze the relation of the estimated SCL-90 scores with the daily reported cumulative case numbers and lasting time of the epidemic among Wuhan and non-Wuhan users. In non-Wuhan users, the estimated scores for all the SCL-90 dimensions significantly increased with the lasting time of the epidemic and the accumulation of cases, except for the interpersonal sensitivity dimension. In Wuhan users, although the estimated scores for all nine SCL-90 dimensions significantly increased with the cumulative case numbers, the magnitude of the changes was generally smaller than that in non-Wuhan users. The mental health of Chinese Weibo users was affected by the daily updated information on case numbers and the lasting time of the COVID-19 outbreak.
关键词：mental health; COVID-19; SCL-90; longitudinal analysis; computerized machine learning models; Sina Weibo mental health ; COVID-19 ; SCL-90 ; longitudinal analysis ; computerized machine learning models ; Sina Weibo
