Digital Transformation in Music Education: A Machine Learning-Based Analysis of Public Awareness and Adoption

Abstract

Music education plays a critical role in students' comprehensive development, enhancing memory, attention, creativity, aesthetic experience, and cultural literacy. Traditional music education faces challenges including limited teaching methods, lack of individualized attention, and insufficient teacher-student interaction, which can constrain students' initiative and creativity. Digital technologies offer new possibilities for music education. Digital music education improves teaching efficiency and quality, supports personalized learning, enhances interaction and engagement, and broadens the learning scope. It also enables sharing of music education resources and flexible learning environments. However, challenges remain: technological accessibility, the digital divide, potential impacts on teaching quality and depth, and teachers' adaptation and training needs. To examine these factors, this research work studies public awareness, adoption, opportunities, and challenges of digital music education through questionnaire data. This work uses Machine Learning (ML) algorithms such as Logistic Regression, Decision Trees, Random Forests, Support Vector Machines, and Extreme Gradient (XG) Boosting to predict likelihood of adoption and identify the most influential factors determining public perception. It is observed that logistic regression outperforms well in terms of accuracy, precision, recall, and F1-score. This investigation offers the way to handle these challenges and analyzes approaches for sustainable digital transformation of music education.