ChatGPT Generated Training Plans for Runners are not Rated Optimal by Coaching Experts, but Increase in Quality with Additional Input Information.

IF 2.4 2区 医学 Q2 SPORT SCIENCES
Peter Düking, Billy Sperlich, Laura Voigt, Bas Van Hooren, Michele Zanini, Christoph Zinner
{"title":"ChatGPT Generated Training Plans for Runners are not Rated Optimal by Coaching Experts, but Increase in Quality with Additional Input Information.","authors":"Peter Düking, Billy Sperlich, Laura Voigt, Bas Van Hooren, Michele Zanini, Christoph Zinner","doi":"10.52082/jssm.2024.56","DOIUrl":null,"url":null,"abstract":"<p><p>ChatGPT may be used by runners to generate training plans to enhance performance or health aspects. However, the quality of ChatGPT generated training plans based on different input information is unknown. The objective of the study was to evaluate ChatGPT-generated six-week training plans for runners based on different input information granularity. Three training plans were generated by ChatGPT using different input information granularity. 22 quality criteria for training plans were drawn from the literature and used to evaluate training plans by coaching experts on a 1-5 Likert Scale. A Friedmann test assessed significant differences in quality between training plans. For training plans 1, 2 and 3, a median rating of <3 was given 19, 11, and 1 times, a median rating of 3 was given 3, 5, and 8 times and a median rating of >3 was given 0, 6, 13 times, respectively. Training plan 1 received significantly lower ratings compared to training plan 2 for 3 criteria, and 15 times significantly lower ratings compared to training plan 3 (p < 0.05). Training plan 2 received significantly lower ratings (p < 0.05) compared to plan 3 for 9 criteria. ChatGPT generated plans are ranked sub-optimally by coaching experts, although the quality increases when more input information are provided. An understanding of aspects relevant to programming distance running training is important, and we advise avoiding the use of ChatGPT generated training plans without an expert coach's feedback.</p>","PeriodicalId":54765,"journal":{"name":"Journal of Sports Science and Medicine","volume":"23 1","pages":"56-72"},"PeriodicalIF":2.4000,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10915606/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Sports Science and Medicine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.52082/jssm.2024.56","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"SPORT SCIENCES","Score":null,"Total":0}
引用次数: 0

Abstract

ChatGPT may be used by runners to generate training plans to enhance performance or health aspects. However, the quality of ChatGPT generated training plans based on different input information is unknown. The objective of the study was to evaluate ChatGPT-generated six-week training plans for runners based on different input information granularity. Three training plans were generated by ChatGPT using different input information granularity. 22 quality criteria for training plans were drawn from the literature and used to evaluate training plans by coaching experts on a 1-5 Likert Scale. A Friedmann test assessed significant differences in quality between training plans. For training plans 1, 2 and 3, a median rating of <3 was given 19, 11, and 1 times, a median rating of 3 was given 3, 5, and 8 times and a median rating of >3 was given 0, 6, 13 times, respectively. Training plan 1 received significantly lower ratings compared to training plan 2 for 3 criteria, and 15 times significantly lower ratings compared to training plan 3 (p < 0.05). Training plan 2 received significantly lower ratings (p < 0.05) compared to plan 3 for 9 criteria. ChatGPT generated plans are ranked sub-optimally by coaching experts, although the quality increases when more input information are provided. An understanding of aspects relevant to programming distance running training is important, and we advise avoiding the use of ChatGPT generated training plans without an expert coach's feedback.

ChatGPT 生成的跑步者训练计划未被教练专家评为最佳,但在输入更多信息后质量会提高。
跑步者可使用 ChatGPT 生成训练计划,以提高成绩或改善健康状况。然而,基于不同输入信息生成的 ChatGPT 训练计划的质量尚不可知。本研究的目的是评估 ChatGPT 根据不同的输入信息粒度为跑步者生成的六周训练计划。ChatGPT 使用不同的输入信息粒度生成了三个训练计划。训练计划的 22 项质量标准来自文献,并由教练专家使用 1-5 李克特量表对训练计划进行评估。弗里德曼测试评估了不同培训计划在质量上的显著差异。培训计划 1、2 和 3 的中位数评分分别为 3 分、0 分、6 分和 13 分。与培训计划 2 相比,培训计划 1 在 3 项标准上的评分明显较低,而与培训计划 3 相比,则明显低 15 倍(p < 0.05)。培训计划 2 在 9 项标准上的评分明显低于培训计划 3(p < 0.05)。ChatGPT 生成的计划被教练专家评为次优,尽管当提供更多输入信息时,质量会有所提高。了解长跑训练计划编制的相关方面非常重要,我们建议在没有专家教练反馈的情况下避免使用 ChatGPT 生成的训练计划。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
5.60
自引率
6.20%
发文量
56
审稿时长
4-8 weeks
期刊介绍: The Journal of Sports Science and Medicine (JSSM) is a non-profit making scientific electronic journal, publishing research and review articles, together with case studies, in the fields of sports medicine and the exercise sciences. JSSM is published quarterly in March, June, September and December. JSSM also publishes editorials, a "letter to the editor" section, abstracts from international and national congresses, panel meetings, conferences and symposia, and can function as an open discussion forum on significant issues of current interest.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信