Design and Application of Machine Learning-Based Evaluation for University Music Teaching

Abstract

Teaching evaluation (TE) is an operational means of music education and management, a value judgment on university-related music teaching activities, with the fundamental purpose of promoting and improving the overall development of the cultivated subjects. With the deepening of quality education, the types and contents of music teaching evaluation (MTE) are being updated and changed, and many universities are gradually introducing music classroom teaching quality evaluation systems. Teaching quality evaluation plays an important role in the development of music teaching and affects the quality of educational evaluation, and is an important guarantee for the continuous reform and development of university music teaching (UMT), as well as an important means for scientific and reasonable management of schools, which plays an irreplaceable role in the development of schools. The evaluation of the quality of university music classroom teaching is a systematic process of analyzing and evaluating the teaching programs, teaching effects, and teaching processes of the music classroom within the school, which is conducive to improving the quality of university music classroom teaching. This article will focus on the overview of university music classroom teaching quality evaluation, analyze its main problems and causes, develop effective improvement measures to solve them, and build a machine learning (ML)-based UMT quality evaluation system. The model quantifies the concept of MTE indexes into definite data as the input of the network, and the comprehensive evaluation results as the output. The method overcomes the subjective factors of the evaluation subject in the evaluation process, but also obtains satisfactory evaluation results with wide applicability.