Real-time Artificial Intelligence Text Analysis for Identifying Burnout Syndromes in High-Performance Athletes
Authors:
- 25 January 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 000253-000258
Abstract
Predicting burnout from texts by using AI necessitates an interdisciplinary approach, combining sports science, psychology, and machine learning. This research is essential to understanding the psychological signs of burnout and the methods to gauge it, coupled with expertise in NLP and sentiment analysis techniques. Collecting athletes’ textual data, like logs or interviews, is crucial, along with possible metrics of stamina or fatigue. The role of AI, in particular significantly advanced models like BERT or GPT-3, is to analyze these texts, discerning underlying sentiments that may indicate burnout. AI can identify impending burnout patterns by correlating text-derived sentiments with physical metrics. This study investigated the feasibility of an AI-driven approach to proactive intervention, allowing timely measures to prevent burnout. Additionally, it allows athletes to customize their training to their mental and physical health, thus extending their careers. AI promises to prioritize athletes’ physical and mental well-being, improving performance and team dynamics. A series of experiments were conducted on two datasets to validate this model. The results are promising.Keywords
Funding Information
- Waseda University
This publication has 12 references indexed in Scilit:
- Precognition of mental health and neurogenerative disorders using AI-parsed text and sentiment analysisActa Universitatis Sapientiae, Informatica, 2023
- A Brief Note on the Standard Error of the Pearson CorrelationCollabra: Psychology, 2023
- Long-term healthcare professionals’ experiences of burnout and correlation between burnout and fatigue: A cross-sectional studyInternational Journal of Occupational Medicine and Environmental Health, 2023
- Athlete burnout and perfectionism in objectively and subjectively assessed sportsInternational Journal of Sports Science & Coaching, 2022
- Visual Object Detection with DETR to Support Video-Diagnosis Using Conference ToolsApplied Sciences, 2022
- On the other Side of Technology: Examining of Different Behavior Patterns with Artificial IntelligenceActa Polytechnica Hungarica, 2022
- Adaptation Strategies for Human-Machine Interactions in Dialect Specific EnvironmentActa Polytechnica Hungarica, 2022
- Using Machine Learning in Burnout Prediction: A SurveyChild and Adolescent Social Work Journal, 2021
- Risk and protective factors for mental health in elite athletes: a scoping reviewInternational Review of Sport and Exercise Psychology, 2019
- Analyzing the Relationship Between Burnout and Depression in Junior Elite AthletesJournal of Clinical Sport Psychology, 2017