Based on big data analysis of the current situation of music teaching in China’s colleges and universities and the innovative development of exploration

Abstract

Abstract This paper develops a cluster analysis model based on big data analytics, which first utilizes ETL tools to extract, clean, and standardize music teaching data from massive data. Then, the preprocessed music teaching data was analyzed using a big data technology platform. Finally, the clustering algorithm has been improved, and the K-means algorithm based on density optimization is designed to cluster the music teaching data. Using this model to analyze the learning behavior of college music classroom yields that the quantitative values of test activities and classroom performance in Classification 1 are only 11 and 14, the quantitative value of classroom performance in Classification 2 is only 9, and the quantitative value of homework group task in Classification 3 is only 9. The analysis shows that the quality of music teachers in colleges and universities is not uniform. The current state of music teaching in colleges and universities is poor, and it is imperative to create and improve music education.