Social Media Reveals Psychosocial Effects of the COVID-19 Pandemic

摘要: Abstract Background The novel coronavirus disease 2019 (COVID-19) pandemic has caused several disruptions in personal and collective lives worldwide. uncertainties surrounding the have also led to multi-faceted mental health concerns, which can be exacerbated with precautionary measures such as social distancing self-quarantining, well societal impacts economic downturn job loss. Despite noting this a “mental tsunami,” psychological effects of COVID-19 crisis remains unexplored at scale. Consequently, public stakeholders are currently limited identifying ways provide timely tailored support during these circumstances. Objective Our work aims insights regarding people’s psychosocial concerns by leveraging media data. We aim study temporal linguistic changes symptomatic expressions context. Methods obtain ∼60M Twitter streaming posts originating from U.S. 24 March-24 May 2020, compare ∼40M comparable period attribute effect on self-disclosure. Using datasets, we self-disclosure terms support. employ transfer learning classifiers that identify language indicative outcomes (anxiety, depression, stress, suicidal ideation) (emotional informational support). then examine over time language, comparing 2020 datasets. Results find all examined significantly increased – ∼14%, ∼5%, both thematically related COVID-19. observe steady decline eventual plateauing pandemic, may been due habituation or supportive policy enacted period. analyses highlight people express very specific contextually crisis. Conclusions studied using data finding compared similar 2019. However, gradually lessened time, suggesting adapted circumstances their “new normal”. revealed expressed professional challenges, healthcare measures, pandemic-related awareness. This shows potential policymakers planning implementing mitigate risks amidst