Computer Data Analysis based on Deep Learning: An Empirical Study on the Impact of Teacher Experience on College Students' Sports Participation

Abstract

Relying on advanced computer data processing technology and deep learning models, this study aims to explore how the experience accumulation of physical education teachers affects college students' sports participation behavior and verify the mediating role of sports motivation. Taking higher vocational colleges in Chengdu as a sample, data were collected through questionnaire surveys, and the structural equation model (SEM) was used to measure and verify the unidimensional construct of teacher experience (TE). The teacher experience construct contains four measurement indicators (TE1, TE2, TE3, and TE4). Its design not only refers to the latest theoretical literature, but also has been reviewed by experts and pre-investigated to ensure content validity. AMOS23.0 software was used for confirmatory factor analysis (CFA). The results showed that the model's various fit indicators were better than the recommended standards (e.g., CMIN/DF=2.962, RMR=0.023, GFI=0.994, AGFI=0.969, CFI=0.996, etc.), indicating that the measurement of teacher experience has good reliability and validity. The empirical results show that teacher experience has a significant positive impact on college students' sports participation. This relationship has both a direct effect and a partial mediating effect through sports motivation. The research results not only provide a theoretical basis for improving the quality of physical education and stimulating students' sports participation, but also provide practical inspiration for improving the training and management model of physical education teachers in colleges and universities. In addition, combined with advanced computer-assisted data analysis technologies such as deep learning models, the accuracy and interpretability of sports participation research have been significantly improved.