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: Sep 25, 2025
Date Accepted: Feb 2, 2026

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

Cross-Cultural Differences in Public Discourse on COVID-19 Vaccination in the United States and South Korea: Cross-Sectional Analysis Using Natural Language Processing

Youm S, Jang SH, Kwak H, Choi J, Yi YJ

Cross-Cultural Differences in Public Discourse on COVID-19 Vaccination in the United States and South Korea: Cross-Sectional Analysis Using Natural Language Processing

JMIR Form Res 2026;10:e84791

DOI: 10.2196/84791

PMID: 41785455

Cross-Cultural Differences in Public Discourse on COVID-19 Vaccination in the U.S. and South Korea: Cross-Sectional Analysis Using Natural Language Processing

  • Sangpil Youm; 
  • Sou Hyun Jang; 
  • Haewoon Kwak; 
  • Jaeyoung Choi; 
  • Yong Jeong Yi

ABSTRACT

Background:

The COVID-19 vaccine was introduced as a crucial tool to combat the pandemic. However, concerns about its effectiveness, side effects, and the spread of misinformation have remained. Prior research has largely relied on survey-based approaches with limited populations. To broaden the perspective on public health concerns, social media offers a wider lens. Our study leverages a social media–based approach to uncover factors influencing vaccine uptake and communication.

Objective:

The present study investigated public discourse about COVID-19 vaccines on community-driven question-and-answer sites in the United States (Quora) and South Korea (Naver Knowledge-iN) to examine information needs and perceptions of vaccination in the two countries.

Methods:

We used a novel method that combined Latent Dirichlet Allocation (LDA) and Top2Vec to analyze the questions on Quora and Naver Knowledge-iN. We also coupled a sentiment analysis with a temporal analysis to examine the answers dynamically.

Results:

Our findings indicated that although the two countries shared five common information needs about the COVID-19 vaccine, South Korea had two unique needs: vaccination appointments and education. The sentiment analysis revealed that Korean users had mostly positive perceptions of the vaccine, while U.S. users had mostly negative perceptions. Furthermore, the sentiment analysis of question-and-answer pairs showed that Korean users had mostly Positive-Positive pairs, whereas U.S. users exhibited Negative-Negative pairs.

Conclusions:

The difference in vaccine perceptions and information needs related to vaccines between the two countries suggests that public trust in the government and vaccines must be improved to increase vaccination rates, highlighting the importance of culturally tailored health communication.


 Citation

Please cite as:

Youm S, Jang SH, Kwak H, Choi J, Yi YJ

Cross-Cultural Differences in Public Discourse on COVID-19 Vaccination in the United States and South Korea: Cross-Sectional Analysis Using Natural Language Processing

JMIR Form Res 2026;10:e84791

DOI: 10.2196/84791

PMID: 41785455

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.