Using ChatGPT in Requirements Prioritization: An Educational Experience in Software Engineering

• Francisca Karolina Queiroz UEA
• Márcia Sampaio Lima UEA

DOI: https://doi.org/10.5753/educomp.2025.5370

Abstract

The teaching of Software Engineering (SE) has been transformed by Generative Artificial Intelligence (AI), expanding possibilities in the teachinglearning process of computing. In SE, AI supports various software development tasks. This study reports an experience with 16 students using ChatGPT to prioritize software requirements for the MVP (Minimum Viable Product). Initially, the students elicited and prioritized the software requirements for MVP implementation. Subsequently, they used ChatGPT to review the prioritization and propose new requirements. ChatGPT corroborated 86.02% of the students’ choices. Despite acknowledging the agility provided, the students reported needing more confidence in the AI’s results.

References

Alonso, S., Kalinowski, M., Ferreira, B., Barbosa, S. D., and Lopes, H. (2023). A systematic mapping study and practitioner insights on the use of software engineering practices to develop mvps. Information and Software Technology, 156:107144.

Arora, C., Grundy, J., and Abdelrazek, M. (2024). Advancing requirements engineering through generative ai: Assessing the role of llms. In Generative AI for Effective Software Development, pages 129–148. Springer.

Beganovic, A., Jaber, M. A., and Abd Almisreb, A. (2023). Methods and applications of chatgpt in software development: a literature review. Southeast Europe Journal of Soft Computing, 12(1):08–12.

Daun, M. and Brings, J. (2023). How chatgpt will change software engineering education. In Proceedings of the 2023 Conference on Innovation and Technology in Computer Science Education V. 1, pages 110–116.

Marques, N., Silva, R. R., and Bernardino, J. (2024). Using chatgpt in software requirements engineering: A comprehensive review. Future Internet, 16(6):180.

Melegati, J., Chanin, R., Sales, A., Prikladnicki, R., and Wang, X. (2020). Mvp and experimentation in software startups: a qualitative survey. In 2020 46th Euromicro Conference on Software Engineering and Advanced Applications (SEAA), pages 322–325. IEEE.

Mendonça, G. D., de Souza Filho, I. P., and Guedes, G. T. A. (2021). A systematic review about requirements engineering processes for multi-agent systems. ICAART (1), pages 69–79.

Mittal, U., Sai, S., Chamola, V., et al. (2024). A comprehensive review on generative ai for education. IEEE Access.

Petrovska, O., Clift, L., Moller, F., and Pearsall, R. (2024). Incorporating generative ai into software development education. In Proceedings of the 8th Conference on Computing Education Practice, pages 37–40.

Ries, E. (2011). The lean startup: How today’s entrepreneurs use continuous innovation to create radically successful businesses. Crown Currency.

Sampaio, S., Lima, M., Rodrigues, E., Meireles, M. A., Pessoa, M., and Conte, T. (2024a). Exploring the use of large language models in requirements engineering education: An experience report with chatgpt 3.5. SBQS 2024.

Sampaio, S., Lima, M., Rodrigues, E., Meireles, M. A., Pessoa, M., and Conte, T. (2024b). Exploring the use of large language models in requirements engineering education: An experience report with chatgpt 3.5.

Sun, J., Liao, Q. V., Muller, M., Agarwal, M., Houde, S., Talamadupula, K., and Weisz, J. D. (2022). Investigating explainability of generative ai for code through scenario-based design. In Proceedings of the 27th International Conference on Intelligent User Interfaces, pages 212–228.

White, J., Hays, S., Fu, Q., Spencer-Smith, J., and Schmidt, D. C. (2024). Chatgpt prompt patterns for improving code quality, refactoring, requirements elicitation, and software design. In Generative AI for Effective Software Development, pages 71–108. Springer.