An Intelligent Evaluation System for College Music Teaching Quality Using EXPSC-WOA and FHCA Algorithms

The college Music course teaching refers to how effectively a teacher delivers spoken English instruction, emphasizing fluency, clarity, pronunciation, and interactive engagement. However, existing works have not focused on analyzing English teaching quality based on student feedback across various categories, such as courses, labs, etc. Therefore, this paper proposes an efficient college Music course teaching quality evaluation system using ExpSC-WOA and FHCA. Initially, the college English learning dataset is pre-processed, followed by data clustering using FHCA. Although the proposed system is designed for evaluating College Music Teaching Quality, the datasets utilized in this study are derived from College English learning environments. This is because both domains share common pedagogical attributes such as student engagement, performance assessment, feedback mechanisms, and session-based learning behaviors. In particular, spoken English learning involves interactive, performance-based evaluation similar to music instruction (e.g. pronunciation, fluency, rhythm, and expression), making it a suitable proxy dataset. Therefore, the proposed framework is domain-adaptive and can be effectively extended to music education scenarios. Then, word embeddings are generated from the pre-processed data using BERT. Afterward, classification is performed using QESMT-GRU based on the extracted features and embedded words. Finally, from the selected attributes and classified output, the quality of Music course teaching is evaluated using AWNBNFIS. Thus, the proposed QESMT-GRU attained an accuracy of 98.4578% in the classification of students’ feedback.