Currently submitted to: JMIR Pediatrics and Parenting
Date Submitted: Mar 31, 2025
Open Peer Review Period: Apr 2, 2025 - May 28, 2025
(currently open for review)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Effectiveness of Anonymous, On-Demand, Real-time Moderated Peer Support in Medicaid-Plan-Sponsored Teens: A Retrospective Analysis of Emotional Relief and Sentiment Change
ABSTRACT
Background:
Teens from low socioeconomic status (SES) households have a higher risk for emotional distress and less access to support. Emotional distress increases the risk of mental health and other downstream chronic conditions. Today, all teens, including those from low SES households use technology pervasively. Real-time moderated digital peer support presents an opportunity to connect low income teens to a safe, evidence-based support resource in real time.
Objective:
The current study focuses on Medicaid-plan-sponsored teens who were given no-cost access to a 24/7, on-demand, anonymous, real-time moderated digital peer support service to better understand the dynamics of how sentiment and emotional states changed throughout the chat conversations.
Methods:
Using OpenAI’s LLM model, GPT-4o-mini, employing a few-shot learning approach, 1005 conversations were evaluated for non-clinical emotional distress variables including sadness, stress, insecurity, loneliness, anger, and anxiety.
Results:
Consistent, statistically significant improvement was observed in all emotional states throughout the conversations, with the greatest reductions seen for anger (46.94%, Wilcoxon signed-rank test P = 2.265 × 10⁻¹⁷), loneliness (31.99%, P = 9.968 × 10⁻²⁰), and stress (31.02%, Wilcoxon signed-rank test P = 2.394 × 10⁻²⁵). There were also smaller reductions in anxiety, sadness, and insecurity over the course of the conversations and a corresponding improvement in overall sentiment (196.78% increase, Wilcoxon signed-rank test P = 1.954 × 10⁻¹⁹).
Conclusions:
Among a cohort of Medicaid-plan-sponsored teens, use of an anonymous, synchronous, real-time moderated digital peer support service was associated with significant reductions in sadness, stress, insecurity, loneliness, anger, and anxiety and a corresponding improvement in optimism by the end of the conversations. These marked reductions in distressing emotions continued as the conversations progressed, reinforcing the potential value of conversation-based engagement on emotional regulation and overall emotional well-being. Teens from low income households face higher incidence of mental health conditions. Digital peer support could be instrumental in easing such emotional distress and addressing the larger teen mental health crisis. Clinical Trial: N/A
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© 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.