Accepted for/Published in: JMIR Public Health and Surveillance
Date Submitted: Apr 11, 2020
Date Accepted: May 18, 2020
Date Submitted to PubMed: May 18, 2020
Insights into COVID-19: Mining Physicians’ Opinions on Social Media
ABSTRACT
Background:
The coronavirus pandemic outbreak is considered the most daunting public health challenge in decades. With no effective treatments and the time needed to develop a vaccine, alternatives approaches are followed to control such pandemic.
Objective:
To identify topics, opinions, and recommendations discussed by medical professionals about the coronavirus pandemic outbreak on social medial platform, Twitter.
Methods:
Using a mixed-method approach blending the capabilities of social media analytics and qualitative analysis, we analyzed coronavirus related tweets posted by medical professionals and examined their content. We used qualitative analysis to explore the collected data in order to identify relevant tweets and uncover important concepts about the phenomenon using qualitative coding. Unsupervised and supervised machine learning techniques and text analysis were used to identify topics and opinions.
Results:
We identified eight topics, namely, actions and recommendations, fighting misinformation, information and knowledge, healthcare system, symptoms and illness, immunity, testing, and infection and transmission. Tweets were mainly focused on actions and recommendations (28%) needed to control the pandemic. Many tweets warned about misleading information (20%) which could lead to more cases infected with the virus. Knowledge and information (9%) about the symptoms (8%) associated with COVID-19, virus infection and transmission (5%), and immunity (7%), as well as concerns about the healthcare systems and workers (9%) and testing (6%) were discussed by medical professionals.
Conclusions:
Findings indicate that Twitter and social media platforms could help identify important and useful knowledge shared by medical professionals during the pandemic outbreak.
Citation
Request queued. Please wait while the file is being generated. It may take some time.