Research on the Reform and Innovation of College Music Teaching Based on Collaborative Filtering Algorithm

Abstract

With the rapid development of artificial intelligence technology, collaborative filtering (CF) algorithms are becoming increasingly widely used in the field of education. This paper aims to explore the application of CF algorithms in the reform and innovation of music teaching in universities, in order to improve teaching effectiveness and students’ learning experience. First, this paper analyzes the problems existing in current music teaching in universities, such as single teaching methods and low student participation. In order to complete the research on the extension of online music systems in music teaching, this paper reused the post filtering paradigm of contextual information and redesigned the two-stage process of the hybrid algorithm. After the initial screening of CF, the algorithm extracts recommendation results with contextual bias based on tag information. Then, based on the improved algorithm, an online music teaching system was implemented. Applying hybrid algorithm intelligent algorithms to university music teaching can not only improve the personalization and interactivity of teaching, but also promote the cultivation of students’ creativity and critical thinking abilities. The experimental results show that the music teaching system using hybrid intelligent algorithms significantly improves students’ learning participation, with an average participation rate increased by 30% compared to traditional teaching methods. At the same time, students’ learning outcomes have also significantly improved, with an average score increase of 15% in music theory exams. And in the assessment of creativity and critical thinking ability, students show stronger thinking activity and innovation ability. In addition, system feedback indicates that over 90% of students are satisfied with the teaching system, believing that it enhances the fun and interactivity of learning.