Evaluating Large Language Models as Mental Health Support Tools for Teenage Athletes
Year: 2025
Type: article
Abstract: This study investigates the potential of Large Language Models (LLMs) as mental health support tools for teenage athletes aged 13-18. Through a survey of 60 teenage athletes across 15 sports, we identified four primary mental health challenges: 68% mentioned performance anxiety, 80.2% mentioned peer pressure, 48% of them had confidence-related stress, and 39% had social comparison/perfectionism issues. Our findings reveal a significant gap between mental health needs and available support, with 78% of athletes attempting to "push through" challenges independently despite 47% expressing need for expert guidance. We evaluated three leading LLMs (ChatGPT-4, Claude 3, and Gemini Pro) using 20 scenario-based prompts derived from survey responses. Results indicate that LLMs show promise in providing accessible, 24/7 support that meets athletes' needs for help during non-traditional hours, with 64% of surveyed athletes open to AI-based support and 73% preferring a hybrid AI-human model. This research contributes to understanding how technology can bridge gaps in mental health support for young athletes while highlighting necessary safeguards and limitations.
Author: Lynn, La Pyae Shane
Language: English
Subfield: Applied Psychology
Field: Psychology
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W7084088183
FWCI:
Cites:
Cited by:
Related to: