A data mining-based evaluation technique for music teaching

Abstract

Musical data mining covers a number of methodologies to successfully apply data mining techniques for music processing, drawing together a multidisciplinary array of top experts. The field of music data acquisition has grown through time to solve the difficulties of obtaining and engaging with enormous amounts of music and associated data, such as styles, artists, lyrics, and reviews. In order to improve the quality of music teaching, a music teaching evaluation based on data mining is proposed. Data mining is becoming more widely accepted as a viable form of inquiry for analyzing data obtained in natural settings. More and more attention is paid to music teaching. Actual data is frequently inadequate, unreliable, and/or lacking in specific behaviors or patterns, as well as including numerous inaccuracies. Preprocessing data is a tried-and-true means of resolving such problems. Music teaching data is divided into three steps after preprocessing, that is, “object and object type,” “music teaching data normalization,” and “data integration.” A model is built with a high-dimensional characteristic distribution and essential parameters of convergent teaching capacity. The experimental results show that the data mining method can be used for music teaching evaluation and has the advantages of short evaluation time, high accuracy, and clear indicators.