The COVID-19 pandemic might lead to more mental health problems. However, few studies have examined sleep problems, depression, and posttraumatic symptoms among the general adult population during the COVID-19 outbreak, and little is known about coping behaviors. This survey was conducted online in China from February 1st to February 10th, 2020. Quota sampling was used to recruit 2993 Chinese citizens aged ≥18 years old. Mental health problems were assessed with the Post-Traumatic Stress Disorders (PTSD) Checklist for the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM-5), the Center for Epidemiological Studies Depression inventory, and the Pittsburgh Sleep Quality Index. Exposure to COVID-19 was measured with questions about residence at outbreak, personal exposure, media exposure, and impact on livelihood. General coping style was measured by the brief Coping Style Questionnaire (SCSQ). Respondents were also asked 12 additional questions about COVID-19 specific coping behaviors. Direct exposure to COVID-19 instead of the specific location of (temporary) residence within or outside the epicenter (Wuhan) of the pandemic seems important (standardized beta: 0.05, 95% confidence interval (CI): 0.02–0.09). Less mental health problems were also associated with less intense exposure through the media (standardized beta: −0.07, 95% CI: −0.10–−0.03). Perceived negative impact of the pandemic on livelihood showed a large effect size in predicting mental health problems (standardized beta: 0.15, 95% CI: 0.10–0.19). More use of cognitive and prosocial coping behaviors were associated with less mental health problems (standardized beta: −0.30, 95% CI: −0.34–−0.27). Our study suggests that the mental health consequences of the lockdown impact on livelihood should not be underestimated. Building on cognitive coping behaviors reappraisal or cognitive behavioral treatments may be most promising.

Background: Detection of depression gained prominence soon after this troublesome disease emerged as a serious public health concern worldwide. Objective: This systematic review aims to summarize the findings of previous studies concerning applying machine learning (ML) methods to text data from social media to detect depressive symptoms and to suggest directions for future research in this area. Methods: A bibliographic search was conducted for the period of January 1990 to December 2020 in Google Scholar, PubMed, Medline, ERIC, PsycINFO, and BioMed. Two reviewers retrieved and independently assessed the 418 studies consisting of 322 articles identified through database searching and 96 articles identified through other sources; 17 of the studies met the criteria for inclusion. Results: Of the 17 studies, 10 had identified depression based on researcher-inferred mental status, 5 had identified it based on users’ own descriptions of their mental status, and 2 were identified based on community membership. The ML approaches of 13 of the 17 studies were supervised learning approaches, while 3 used unsupervised learning approaches; the remaining 1 study did not describe its ML approach. Challenges in areas such as sampling, optimization of approaches to prediction and their features, generalizability, privacy, and other ethical issues call for further research. Conclusions: ML approaches applied to text data from users on social media can work effectively in depression detection and could serve as complementary tools in public mental health practice.

Background: The Coronavirus Diseases (COVID-19) pandemic is a global public health challenge and provides an opportunity to investigate the unclear relationship between risk perception, social support, and mental health. This study aims to examine the association between risk perception and mental health while taking social support as a moderator. Methods: An online cross-sectional study recruiting 2993 participants was conducted in China, from 1st to 10th, February 2020. The relationship between risk perception, social support, and mental health was examined using multivariate linear regression analyses. Results: This study indicated that risk perception was associated with a higher level of mental health symptoms. The subscale “Perceived uncontrollability” seemed to present a stronger correlation with depressive symptoms (Beta=0.306) and post-traumatic stress disorder (PTSD) symptoms (Beta=0.318) than the subscale “Perceived Severity” did. Moreover, social support moderated the relationship between perceived uncontrollability and mental health symptoms. Conclusion: In the context of the COVID-19 pandemic, it is necessary to design mental health strategies and programs from a risk perception perspective (more mental health strategies should be delivered to build reasonable risk perception), while social support from family and friends may be protective to against depressive symptoms and PTSD symptoms. There is a demand for mental health intervention from a risk perception perspective.