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 Diabetes

Date Submitted: May 1, 2024
Date Accepted: Oct 22, 2024

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

Toward Personalized Digital Experiences to Promote Diabetes Self-Management: Mixed Methods Social Computing Approach

Singh T, Roberts K, Fujimoto K, Wang J, Johnson C, myneni s

Toward Personalized Digital Experiences to Promote Diabetes Self-Management: Mixed Methods Social Computing Approach

JMIR Diabetes 2025;10:e60109

DOI: 10.2196/60109

PMID: 39773324

PMCID: 11731698

Towards personalized digital experiences to promote diabetes self-management: A mixed-methods social computing approach

  • Tavleen Singh; 
  • Kirk Roberts; 
  • Kayo Fujimoto; 
  • Jing Wang; 
  • Constance Johnson; 
  • sahiti myneni

ABSTRACT

Background:

Type 2 Diabetes affects nearly 34.2 million adults and is the seventh leading cause of death in the United States. Online health communities have emerged as avenues to provide social support to individuals engaging in diabetes self-management (DSM). The analysis of online peer interactions and social connections can improve our understanding of the factors underlying behavior change which can inform the development of personalized DSM interventions.

Objective:

Our objective is to apply our methodology using mixed-methods approach to a) characterize the role of context-specific social influence patterns in DSM and b) derive interventional targets that enhance individual engagement in DSM.

Methods:

Using the peer messages from American Diabetes Association (ADA) support community for DSM (n = ~73k peer interactions from 2014-2021), a) labeled set of peer interactions was generated (n = 1,501 for ADA) through manual annotation; b) deep learning models were used to scale the qualitative codes to the entire datasets; c), the validated model was applied to perform a retrospective analysis; and d) social network analysis (SNA) techniques were used to portray large-scale patterns and relationships among the aforementioned communication dimensions embedded in peer interactions.

Results:

With additional in-domain pre-training, bidirectional encoder representations from Transformers (BERT) outperformed other deep learning models on all classification tasks. Our results suggest that the community users exposed to other users by expressing specific content using specific SAs tended to engage more in the community.

Conclusions:

In this study, we characterize the role of social influence in DSM as observed in large-scale social media datasets. Implications for multicomponent digital interventions is discussed.


 Citation

Please cite as:

Singh T, Roberts K, Fujimoto K, Wang J, Johnson C, myneni s

Toward Personalized Digital Experiences to Promote Diabetes Self-Management: Mixed Methods Social Computing Approach

JMIR Diabetes 2025;10:e60109

DOI: 10.2196/60109

PMID: 39773324

PMCID: 11731698

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.