A Hybrid SEM-Neural Network Method for Identifying Influential Factors of Academic Motivation of Students Majoring in Traditional Chinese Medicine

Abstract

Introduction: The rapid advancement of learning platforms has greatly improved instruments for vocational English instruction and promoted autonomous learning. To follow the trend, educational participants (faculty, teacher, peer, and student) must change their management policies, attitudes, roles, and psychological condition.
Methods：This study used Carroll Model of School Learning to examine factors affecting student academic motivation from macro, meso, and micro perspectives. The model was validated using a multi-analytic approach using Structural Equation Modelling (SEM), and the results were used as inputs for a neural network model to predict acceptance factors. 336 Chinese TCM majors provided data.
Results: The results show that internal and external elements are crucial to developing an academic atmosphere that motivates pupils. It showed that Carroll's Model of School Learning could employ SEM’s causal analysis and ANN's nonlinearity to produce more trustworthy academic motivation influencing factor analysis results.
Discussion: This study's unique methodology and findings will add to the literature on learning platform adoption in TCM education and give a novel conceptual framework from macro, meso, and micro perspectives. This will boost instructor, teacher, and student performance and academic success.