Use of Decision Trees to Evaluate the Impact of a Holistic Music Educational Approach on Children with Special Needs

• Main Authors: Liza Lee, Ying-Sing Liu
• Format: Article
• Language: English
• Published: MDPI AG 2021-01-01
• Series: Sustainability
• Subjects: special early childhood education; HMEAYC; data mining; pre-assessment learning effectiveness; sustainable development
• Online Access: https://www.mdpi.com/2071-1050/13/3/1410

In this study, decision trees were used to develop a pre-assessment model to help ascertain the impact of music education on children with special needs. The focus of the study was the application of an educational curriculum for 16 weeks, five sessions of 40 min duration per week, using the Holistic Music Educational Approach for Young Children (HMEAYC). The pilot program was implemented with children with special needs to measure its learning effectiveness. The methodology proved a better indicator for improved learning and a better measure of learning effectiveness. Statistical tests confirmed significant improvements in the values of the learning evaluation indices measured by HMEAYC after its implementation in children with special needs, supporting the positive effect of the implementation of HMEAYC for Taiwan’s special needs young children. For children with better learning results, the accuracy of the decision tree model was 84.0% for in-sample and the sensitivity equaled 98.0%. The results support the future development of evaluation models through machine learning languages, pre-assessment of the effectiveness of the implementation of HMEAYC, and the use of continuous investment in educational resources to improve the efficiency of special early childhood education in resource consumption for sustainable development.