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: Dec 16, 2024
Date Accepted: Mar 28, 2025

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

Patient Voices in Dialysis Care: Sentiment Analysis and Topic Modeling Study of Social Media Discourse

Shankar R, Qian X, Bundele A

Patient Voices in Dialysis Care: Sentiment Analysis and Topic Modeling Study of Social Media Discourse

J Med Internet Res 2025;27:e70128

DOI: 10.2196/70128

PMID: 40372782

PMCID: 12123232

Patient Voices in Dialysis Care: A Sentiment Analysis and Topic Modeling Study of Social Media Discourse

  • Ravi Shankar; 
  • Xu Qian; 
  • Anjali Bundele

ABSTRACT

Background:

End-stage kidney disease (ESKD) patients undergoing dialysis face significant physical, psychological, and social challenges that impact their quality of life. Social media platforms like X.com (formerly Twitter) have become important outlets for these patients to share experiences and exchange information.

Objective:

This study aimed to uncover key themes, emotions, and challenges expressed by the dialysis community on X.com over an 18-year period from April 2006 to August 2024 by leveraging natural language processing techniques, specifically sentiment analysis and topic modeling.

Methods:

Sentiment analysis using the VADER model classified the emotional tone of 7,543 dialysis-related posts. Latent Dirichlet Allocation (LDA) topic modeling was applied to 4,059 posts to discover latent semantic themes. Sentiment distribution across the identified topics was analyzed. An in-depth thematic analysis, supported by representative patient quotes, provided rich insights into the lived experiences of dialysis patients.

Results:

Sentiment analysis revealed 49.2% positive, 26.2% negative, and 24.7% neutral sentiment posts. LDA identified 8 key themes: medical procedures and outcomes, daily life impact, risks and complications, patient education and support, healthcare access and costs, symptoms and side effects, patient experiences and socioeconomic challenges, and diet and fluid management. Negative sentiment was high for daily life impact, while education and support skewed more positive. The thematic analysis highlighted the multidimensional nature of life on dialysis.

Conclusions:

This study provides a comprehensive, data-driven understanding of the complex lived experiences of dialysis patients shared on social media over an 18-year period. The findings underscore the need for more holistic, patient-centered care models and policies that address the multidimensional challenges illuminated by patients' voices. Social media data offers valuable insights for improving dialysis care and patient support.


 Citation

Please cite as:

Shankar R, Qian X, Bundele A

Patient Voices in Dialysis Care: Sentiment Analysis and Topic Modeling Study of Social Media Discourse

J Med Internet Res 2025;27:e70128

DOI: 10.2196/70128

PMID: 40372782

PMCID: 12123232

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.