An Experience Report on the Use of ChatGPT in Software Requirements Specification

• Iuri V. F. Costa UFPA
• Igor E. F. Costa UFPA

Abstract

Requirements specification is a crucial stage in software development. This study reports the experience of using Generative Artificial Intelligence (AI) as a support tool in this process. It explores how such technologies can enhance and accelerate complex tasks, particularly the generation of user stories (US) with acceptance criteria and field dictionaries. The results highlight benefits, challenges, and implications for professional practice, contributing to a deeper understanding of the applicability and effectiveness of generative AIs in software requirements engineering.

Keywords: Generative AI, Requirements Specification, Software Engineering

References

Feuerriegel, S.; Hartmann, J. J. C. and Zschech, P. (2024). Generative ai. In Bus Inf Syst Eng 66, 111–126. DOI: 10.1007/s12599-023-00834-7.

Khojah, R.; Mohamad, M. L. P. and Neto, F. (2024). Beyond code generation: An observational study of chatgpt usage in software engineering practice. In Proc. ACM Softw. Eng. 1, FSE, Article 81. DOI: 10.1145/3660788.

Marques, N.; Silva, R. and Bernadino, J. (2024). Using chatgpt in software requirements engineering: A comprehensive review. In Future Internet Journal. DOI: 10.3390/fi16060180.

Ronanki, K.; Berger, C. and Horkoff, J. (2023). Investigating chatgpt’s potential to assist in requirements elicitation processes. In 2023 49th Euromicro Conference on Software Engineering and Advanced Applications (SEAA). [link].

Sommerville, I. (2011). Software engineering. In 9th Edition. Addison-Wesley, Boston.

Yeow, J.; Muhammad, R. and Majid, N. (2024). An automated model of software requirement engineering using gpt-3.5. In 2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS). [link].

Zhang, J.; Chen, Y. N. N. W. Y. and Liu, C. (2023). Empirical evaluation of chatgpt on requirements information retrieval under zero-shot setting. In Proceedings of the 2023 International conference on intelligent computing and next generation networks (ICNGN). [link].