TY - JOUR
T1 - LSEL
T2 - A lightweight deep learning model for social-emotional classification of classical music
AU - Lin, Yuan Jin
AU - Chou, Yu Chi
AU - Chien, Shan Ken
AU - Chao, Pen Chiang
AU - Yeh, Kuang Kai
AU - Peng, Yen Chia
AU - Tsao, Chen Hao
AU - Chen, Chih Yun
AU - Chen, Shih Lun
AU - Li, Kuo Chen
AU - Tu, Wei Chen
N1 - Publisher Copyright:
© 2025 The Author(s).
PY - 2026/3
Y1 - 2026/3
N2 - Background/Objectives Social-emotional learning (SEL) plays a crucial role in special education, yet current assessment approaches rely heavily on subjective teacher observation, which can be time-consuming and difficult to standardize. Music provides a meaningful medium for evaluating emotional competencies, creating an opportunity for artificial intelligence to support more objective and scalable SEL assessment. Methods We propose a lightweight social-emotional music classification model, termed LSEL, designed to identify three SEL-related competencies: Empathetic Perspective-Taking, Outlook, and Problem-Solving. LSEL utilizes 40×128 mel-frequency cepstral coefficient as input to capture core spectral–temporal characteristics relevant to SEL perception. Moreover, we provided an open-source SEM dataset for domain experts, utilizing 591 samples, which consisted of 194 Empathetic, 214 Outlook, and 183 Perspective-Taking samples, to analyze LSEL performance. Results LSEL reaching an average accuracy of 96.55 % and mAP of 99.29 % across experiments. With Cohen’s κ averaging 94.32 % and R² reaching 94.15 %, indicating high consistency with ground-truth. Per-category accuracies were similarly stable, including 96.95 % for Empathetic Perspective-Taking, 95.16 % for Outlook, and 95.36 % for Problem-Solving. Conclusions The lightweight LSEL framework offers an effective and robust solution for social-emotional music classification, supporting objective SEL assessment in educational contexts. The release of the SEM dataset further contributes to a valuable resource for advancing AI-assisted SEL research.
AB - Background/Objectives Social-emotional learning (SEL) plays a crucial role in special education, yet current assessment approaches rely heavily on subjective teacher observation, which can be time-consuming and difficult to standardize. Music provides a meaningful medium for evaluating emotional competencies, creating an opportunity for artificial intelligence to support more objective and scalable SEL assessment. Methods We propose a lightweight social-emotional music classification model, termed LSEL, designed to identify three SEL-related competencies: Empathetic Perspective-Taking, Outlook, and Problem-Solving. LSEL utilizes 40×128 mel-frequency cepstral coefficient as input to capture core spectral–temporal characteristics relevant to SEL perception. Moreover, we provided an open-source SEM dataset for domain experts, utilizing 591 samples, which consisted of 194 Empathetic, 214 Outlook, and 183 Perspective-Taking samples, to analyze LSEL performance. Results LSEL reaching an average accuracy of 96.55 % and mAP of 99.29 % across experiments. With Cohen’s κ averaging 94.32 % and R² reaching 94.15 %, indicating high consistency with ground-truth. Per-category accuracies were similarly stable, including 96.95 % for Empathetic Perspective-Taking, 95.16 % for Outlook, and 95.36 % for Problem-Solving. Conclusions The lightweight LSEL framework offers an effective and robust solution for social-emotional music classification, supporting objective SEL assessment in educational contexts. The release of the SEM dataset further contributes to a valuable resource for advancing AI-assisted SEL research.
KW - Classic music feature extraction
KW - Deep learning application
KW - Music augmentation
KW - Social emotional learning
UR - https://www.scopus.com/pages/publications/105026342342
UR - https://www.scopus.com/pages/publications/105026342342#tab=citedBy
U2 - 10.1016/j.mlwa.2025.100832
DO - 10.1016/j.mlwa.2025.100832
M3 - Article
AN - SCOPUS:105026342342
SN - 2666-8270
VL - 23
JO - Machine Learning with Applications
JF - Machine Learning with Applications
M1 - 100832
ER -