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 Formative Research

Date Submitted: Mar 7, 2022
Open Peer Review Period: Mar 6, 2022 - May 1, 2022
Date Accepted: Aug 23, 2022
Date Submitted to PubMed: Aug 25, 2022
(closed for review but you can still tweet)

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

Actions Speak Louder Than Words: Sentiment and Topic Analysis of COVID-19 Vaccination on Twitter and Vaccine Uptake

Yousef M, Dietrich T, Rundle-Thiele S

Actions Speak Louder Than Words: Sentiment and Topic Analysis of COVID-19 Vaccination on Twitter and Vaccine Uptake

JMIR Form Res 2022;6(9):e37775

DOI: 10.2196/37775

PMID: 36007136

PMCID: 9484485

Actions Speak Louder Than Words: A Sentiment and Topic Analysis of COVID-19 Vaccination on Twitter and Vaccine Uptake

  • Murooj Yousef; 
  • Timo Dietrich; 
  • Sharyn Rundle-Thiele

ABSTRACT

Background:

The lack of trust in vaccines is a major contributor to vaccine hesitancy. To help overcome vaccine hesitancy, the Australian government launched multiple public health campaigns aiming to encourage COVID-19 vaccine uptake. This sentiment analysis examines the effect of public health campaigns along with other COVID-19 related events on sentiment and vaccine uptake.

Objective:

The aims of this study were twofold. First, this study examined the relationship between sentiment and COVID-19 vaccine uptake. Second, this paper studied the range of government actions to consider which events positively impacted public sentiment.

Methods:

Using machine learning methods, 137,523 publicly available English tweets containing COVID-19 vaccine related keywords between February and October 2021 were collected in Australia. The study employs machine learning methods to extract topics and sentiments relating to COVID-19 vaccination on Twitter. The relationship between public vaccination sentiment on Twitter and vaccine uptake were examined.

Results:

Most tweets expressed negative sentiment (score=91052, 66%) over positive (score=21686, 16%) and neutral (score=24785, 18%) sentiments in the collected tweets. Topics discussed within the study timeframe include the availability of the COVID-19 vaccines, safety of taking the vaccine and the role of the government in the vaccine rollout. A significant positive correlation between negative sentiment and daily doses administered were evident r(267) = .15, p<.05, with positive sentiment showing opposite direction of effect. Public health campaigns, lockdowns and anti-vaccine protests increased negative sentiment significantly (p<.05) while vaccine mandates had no significant effect on sentiment.

Conclusions:

Findings show negative sentiment was more prevalent on Twitter during the Australian vaccine rollout, but vaccine uptake remained high. Australians expressed anger at the slow rollout and the limited availability of the vaccine during the study period. Public health campaigns along with lockdowns and anti-vaccine rallies increased negative sentiment, while news of vaccine availability for the public and government acquisition of more doses were key government actions capable of reducing negative sentiment. The findings can be used to inform government communication planning.


 Citation

Please cite as:

Yousef M, Dietrich T, Rundle-Thiele S

Actions Speak Louder Than Words: Sentiment and Topic Analysis of COVID-19 Vaccination on Twitter and Vaccine Uptake

JMIR Form Res 2022;6(9):e37775

DOI: 10.2196/37775

PMID: 36007136

PMCID: 9484485

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.

Advertisement