Scoring Instructional Utterances in Guitar Lessons Using Semantic Labels and LLM

This study examines the utility of semantically grounded labels in private music instruction, focusing on how they capture instructional intent and identify important teaching utterances. Our prior work introduced a framework for semantic analysis of classical guitar lessons, annotating teacher utterances with six Instructional Content Labels (ICL): Giving Subjective Information, Giving Objective Information, Asking Question, Giving Feedback, Giving Practice, and Giving Advice. In this study, we extend this framework by developing an ICL-weighted scoring method that combines utterance length with semantic weights to highlight instructionally significant discourse. We also reinterpret ICL categories for real-time spoken instruction, assigning higher weights to actionable guidance. To validate this approach, we compared our scoring outputs against rankings generated by multiple large language models—GPT-4.5, GPT-4o, and Claude Opus 4—across 24 classical guitar lessons. All models showed significantly stronger alignment with ICL-weighted scores than length-only baselines. Claude Opus 4 achieved near-perfect correlation (ρ = 0.993), while GPT-4.5 also demonstrated strong alignment (ρ = 0.902). These findings suggest that ICL-weighted scoring can capture instructional priorities and that general-purpose LLMs may approximate domain-specific judgments. The framework may provide a foundation for automated instructional analysis in music education.