Emergency Physician Twitter Use in the COVID-19 Pandemic as a Potential Predictor of Impending Surge: Retrospective Observational Study
Sentiment Analysis
Pandemic
DOI:
10.2196/28615
Publication Date:
2021-04-23T10:16:23Z
AUTHORS (6)
ABSTRACT
The early conversations on social media by emergency physicians offer a window into the ongoing response to COVID-19 pandemic.This retrospective observational study of physician Twitter use details how health care crisis has influenced discourse online and this may have as harbinger ensuing surge.Followers three main professional organizations were identified using Twitter's application programming interface. They their followers included in if they explicitly US-based physicians. Statuses, or tweets, obtained between January 4, 2020, when new disease was first reported, December 14, vaccination began. Original tweets underwent sentiment analysis previously validated Valence Aware Dictionary Sentiment Reasoner (VADER) tool well topic modeling latent Dirichlet allocation unsupervised machine learning. trends then correlated with daily change cases inpatient bed utilization.A total 3463 produced 334,747 unique English-language during period. Out participants, 910 (26.3%) stated that training, 466 902 (51.7%) participants who provided gender men. Overall tweet volume went from pre-March 2020 mean 481.9 (SD 72.7) 1065.5 257.3) thereafter. Parameter number tuning led 20 topics, coherence 0.49. Except for week June 4 days November, dominated system (45,570/334,747, 13.6%). Discussion pandemic response, epidemiology, clinical jointly found moderately correlate hospital utilization (Pearson r=0.41), occurrence "covid," "coronavirus," "pandemic" texts (r=0.47). Momentum demonstrated sustained crossing 7- 28-day moving averages, occurred an average 45.0 12.7) before peak across country four most contributory states.COVID-19 discussion among correlates precede rising burden. This study, therefore, begins depict extent which affected field medicine suggests potential avenue understanding predictors surge.
SUPPLEMENTAL MATERIAL
Coming soon ....
REFERENCES (69)
CITATIONS (18)
EXTERNAL LINKS
PlumX Metrics
RECOMMENDATIONS
FAIR ASSESSMENT
Coming soon ....
JUPYTER LAB
Coming soon ....