Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: JMIR Public Health and Surveillance

Date Submitted: Apr 20, 2021
Date Accepted: Sep 18, 2021
Date Submitted to PubMed: Sep 28, 2021

The final, peer-reviewed published version of this preprint can be found here:

Examining the Utility of Social Media in COVID-19 Vaccination: Unsupervised Learning of 672,133 Twitter Posts

Liew TM, Lee CS

Examining the Utility of Social Media in COVID-19 Vaccination: Unsupervised Learning of 672,133 Twitter Posts

JMIR Public Health Surveill 2021;7(11):e29789

DOI: 10.2196/29789

PMID: 34583316

PMCID: 8568045

Examining the Utility of Social Media in COVID-19 Vaccination: Unsupervised Learning of 672,133 Twitter Posts

  • Tau Ming Liew; 
  • Cia Sin Lee

ABSTRACT

Background:

Although COVID-19 vaccines have recently become available, efforts in global mass vaccination can be hampered by the widespread issue of vaccine hesitancy.

Objective:

This study utilized social media data to capture close-to-real-time public perspectives and sentiments on COVID-19 vaccine, with the intention to identify useful strategies that may improve vaccine uptake in ongoing COVID-19 vaccination drive.

Methods:

Twitter was searched for feeds related to ‘COVID-19’ and ‘vaccine’, over an eleven-week period after 18th November 2020 (following press release on the first effective vaccine). An unsupervised machine-learning approach (Structural Topic Modelling) was used to identify topics from tweets, with each topic further grouped into themes using manually conducted thematic analysis. Sentiment analysis of the tweets was also performed, using a rule-based machine-learning model (VADER).

Results:

Tweets related to COVID-19 vaccine were posted by individuals around the world (n=672133). Six overarching themes could be identified – Emotional reactions related to COVID-19 vaccine (19.3%), Public concerns related to COVID-19 vaccine (19.6%), Discussions on news related to COVID-19 vaccine (13.3%), Public health communications on COVID-19 vaccine (10.3%), Discussions on approach to COVID-19 vaccination drive (17.1%), and Discussions on distribution of COVID-19 vaccine (20.3%). The 6 themes demonstrated variations over time as well as across continents. Tweets with negative sentiment largely fell within the themes of Emotional reactions and Public concerns.

Conclusions:

The findings may be summarized into an explanatory model to outline key drivers of COVID-19 vaccination, as well as inform strategies to improve vaccine uptake. The findings also illustrate 3 key roles of social media in COVID-19 vaccination – for surveillance and monitoring, as a communication platform, and for evaluation of government responses. Clinical Trial: Not Applicable


 Citation

Please cite as:

Liew TM, Lee CS

Examining the Utility of Social Media in COVID-19 Vaccination: Unsupervised Learning of 672,133 Twitter Posts

JMIR Public Health Surveill 2021;7(11):e29789

DOI: 10.2196/29789

PMID: 34583316

PMCID: 8568045

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.