A Study on Behavioural Characterisation of Music Learners and Optimisation of Teaching Strategies Based on Data Mining

With the development of big data technology, the field of music education has also begun to use data mining technology to analyze learners’ behavioral characteristics in order to provide better music teaching optimization strategies. In this paper, we design a music teaching model based on flipped classrooms and analyze the characteristics of students’ questioning behaviors in the classroom through analysts’ and students’ pre-course preparations, in-course analyses, and post-course feedback in an intelligent teaching environment. And using the iFIAS coding model, the behavioral characteristics of teacher-student interactions in the music-flipped classroom are coded and analyzed. In addition, this paper evaluates the teaching effect of the music-flipped classroom using a variety of teaching effect research methods. The rate of student analytical, evaluative, and comprehensive questioning increased by 12.02%, 12.30%, and 5.65%, respectively, in the music-flipped classroom. The average rate of teacher speech in the flipped classroom was 41.77%, and student speech was 28.47%, both of which showed optimized effects over the standard values. Students recognize the music-based flipped classroom teaching model proposed in this paper, and most of them give it a rating above 4 points. Students in the experimental group showed significant differences in music skill level, music learning interest, learning attitude, and independent learning ability after the experiment compared to the control group (P < 0.5). This study confirms that the flipped classroom can be used as an optimization strategy in music teaching.