ABSTRACT

This study explores the educational potential of prompt engineering in AI-based music creation, focusing on the generative music platform SUNO. By designing prompts based on five variables—genre, instrument, mood, tempo, and technique—I generated and analyzed corresponding 120 audio samples to examine how prompt design affects musical outcomes in school music learning contexts. By using audio feature extraction and quantitative analyses such as similarity matrices, clustering, and dimensionality reduction, I found that detailed and well-structured prompts led to distinct and predictable musical results. In particular, prompts sharing key elements such as instrument or technique produced highly similar audio output, while more varied prompts yielded greater diversity. These findings highlight that prompt engineering can serve as a pedagogical strategy to guide student creativity, support process-oriented learning, and facilitate reflective music inquiry. Based on its finding, this study lays a practical foundation for the educational value of prompt-based AI music creation activities in music education.

Keyword :

REFERENCES

1. Dewey, J. (1933). How we think: A restatement of the relation of reflective thinking to the educative process. D.C. Heath and Company.
2. Dhariwal, P., Jun, H., Payne, C., Kim, J. W., Radford, A., & Sutskever, I. (2020). Jukebox: A generative model for music. arXiv. https://arxiv.org/abs/2005.00341
3. Engel, J., Agrawal, K. K., Chen, S., Gulrajani, I., Donahue, C., & Roberts, A. (2019). GANSynth: Adversarial neural audio synthesis. arXiv. https://arxiv.org/abs/1902.0871
4. Chaiklin, S. (2003). The zone of proximal development in Vygotsky's analysis of learning and instruction. In A. Kozulin, B. Gindis, V. Ageyev, & S. Miller (Eds.), Vygotsky's educational theory in cultural context (pp. 39-64). Cambridge University Press. https://doi.org/10.1017/CBO9780511840975.004 [Crossref]
5. Kim, Y. H. (2024). A study on the development and effectiveness of a strategic model for middle school creative classes utilizing generative AI platforms. Korean Journal of Research in Music Education, 53(3), 1-22. https://doi.org/10.30775/KMES.53.3.01 [Crossref]
6. Lee, H. L., & Shin, G. H. (2023). A study on teaching and learning methods for secondary music creation projects using artificial intelligence(AI). Journal of Music Education Science, 55(1), 63-82. https://doi.org/10.30832/JMES.2023.55.63 [Crossref]
7. Liu, V., & Chilton, L. (2022). Design guidelines for prompt engineering text-to-image generative models. In Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI '22) (pp. 1-23). ACM. https://doi.org/10.1145/3491102.3501825 [Crossref]
8. Park, D. H. (2024). A study on the design of the music class using OpenAI authoring tools: Focusing on generative AI authoring tools based on prompt. Journal of Future Music Education, 9(1), 55-81.
9. Park, E. B. (2024). Analysis of the music works by an AI music generator and consideration of its music educational implications. Korean Journal of Research in Music Education, 53(1), 75-100. https://doi.org/10.30775/KMES.53.1.75 [Crossref]
10. Park, E. B., & Yang, J. M. (2023). Orientation of music creative education according to the development of AI music generator. Journal of Music Education Science, 56, 1-27. https://doi.org/10.30832/JMES.2023.56.1 [Crossref]
11. Sturm, B. L., Ben-Tal, O., Monaghan, Ú., Collins, N., Herremans, D., Chew, E., & Pachet, F. (2019). Machine learning research that matters for music creation: A case study. Journal of New Music Research, 48(1), 36-55. https://doi.org/10.1080/09298215.2018.1515233 [Crossref]
12. Vygotsky, L. S. (1978). Mind in society: The development of higher psychological processes. Harvard University Press.
13. Yang, J. M. (2024). Pre-service teachers' perception about the educational value of AI music generator Suno. Korean Journal of Arts Education, 22(4), 233-254.