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: Journal of Medical Internet Research

Date Submitted: May 13, 2025
Date Accepted: Jul 16, 2025

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

Public Attention to Mpox in China During the Pandemic: Qualitative Analysis of TikTok Data Using Latent Dirichlet Allocation Topic Modeling

Luo D, Xu J, Jiang Y, Tan M, Yao Y, He L, Ma J, Dong W, Luo W, Zhou C

Public Attention to Mpox in China During the Pandemic: Qualitative Analysis of TikTok Data Using Latent Dirichlet Allocation Topic Modeling

J Med Internet Res 2025;27:e77424

DOI: 10.2196/77424

PMID: 40839789

PMCID: 12369990

Public Attention to Mpox in China During the Pandemic: A Qualitative Analysis of TikTok Data Using LDA Topic Modeling

  • DongHang Luo; 
  • Jie Xu; 
  • Yaoyao Jiang; 
  • Mengnan Tan; 
  • Yaping Yao; 
  • Lin He; 
  • Jing Ma; 
  • Wei Dong; 
  • Wei Luo; 
  • Chu Zhou

ABSTRACT

Background:

Mpox has re-emerged as a global public health concern. With the growing reliance on social media for health information dissemination, understanding public perception through these platforms is essential for designing more effective health promotion strategy.

Objective:

This study aims to analyze TikTok data related to mpox using Latent Dirichlet Allocation(LDA) modeling to extract key topics and inform targeted health communication strategies for mpox prevention and control.

Methods:

We collected TikTok data related to "Mpox" from April 1, 2022, to March 31, 2025, using the Aisou Jisou system. Search Index trends and Target Group Index (TGI) were analyzed by time, gender, age group, and province. LDA was applied to extract latent topics from associated search terms and comments. Topic evolution was further analyzed during four peak months of public interest to track changes in discourse.

Results:

Four major search peaks were identified, coinciding with key events such as the WHO's mpox declarations and domestic case surges. Younger users, particularly those aged 18-23, showed the highest levels of engagement; Beijing, Tianjin, and Jilin reported the highest regional TGI. LDA modeling identified eight primary topics, including transmission and prevention, vaccine-related concerns, symptom recognition, case discovery, and misinformation. Public concerns shifted over time from general disease knowledge to stigmatization, vaccine distrust, and conspiracy theories. Sankey diagrams revealed how public attention migrated across topics at different stages of the epidemic.

Conclusions:

TikTok provides real-time insight into public perception during mpox outbreaks but also amplifies misinformation and stigmatizing narratives. Public health authorities should leverage such platforms for timely communication while addressing false information and social bias. Tailored strategies are needed to improve health literacy, reduce stigma, and support outbreak preparedness and response.


 Citation

Please cite as:

Luo D, Xu J, Jiang Y, Tan M, Yao Y, He L, Ma J, Dong W, Luo W, Zhou C

Public Attention to Mpox in China During the Pandemic: Qualitative Analysis of TikTok Data Using Latent Dirichlet Allocation Topic Modeling

J Med Internet Res 2025;27:e77424

DOI: 10.2196/77424

PMID: 40839789

PMCID: 12369990

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.