Developing a personalized chat-based AI model for enhanced sports education: a case study

Guan Li; Xinxin Huang

doi:10.1117/12.2684595

19 October 2023 Developing a personalized chat-based AI model for enhanced sports education: a case study

Guan Li, Xinxin Huang

Proceedings Volume 12709, Fourth International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2023); 127096F (2023) https://doi.org/10.1117/12.2684595
Event: Fourth International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2023), 2023, Nanjing, China

Abstract

The chat-based AI model is an emerging technology that has shown great potential for enhancing sports education. The aim of this study is to develop a personalized chat-based AI model for sports education using machine learning algorithms. To achieve this aim, we collected sports-related data through web scraping and preprocessed it using natural language processing techniques. We then trained the General Pre-trained Transformer 2 (GPT-2) model on this data and fine-tuned it for sports education using PyTorch, Adam optimization, cross-entropy loss, and a validation set. The model was evaluated based on its accuracy, coherence, relevance, and ease of use using a pilot study. The results showed that the personalized chat-based AI model was effective in providing customized sports education, with an overall accuracy of 84.5%, coherence of 81%, relevance of 79%, and ease of use of 81%. This study demonstrates the potential of chat-based AI models in changing the way sports education is delivered and highlights the importance of data collection and preprocessing in building accurate and effective models.

Citation Download Citation

Guan Li and Xinxin Huang "Developing a personalized chat-based AI model for enhanced sports education: a case study", Proc. SPIE 12709, Fourth International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2023), 127096F (19 October 2023); https://doi.org/10.1117/12.2684595

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available