Using ChatGPT in Software Requirements Engineering: A Comprehensive Review

被引：18

作者：

Marques, Nuno ^{[1
]}

Silva, Rodrigo Rocha ^{[2
,3
]}

Bernardino, Jorge ^{[1
,2
]}

机构：

[1] Polytech Univ Coimbra, Coimbra Inst Engn ISEC, Rua Pedro Nunes, P-3030199 Coimbra, Portugal

[2] Ctr Informat & Syst Univ Coimbra CISUC, Polo 2, P-3030290 Coimbra, Portugal

[3] Sao Paulo Technol Coll, FATEC Mogi das Cruzes, Mogi Das Cruzes, Brazil

来源：

FUTURE INTERNET | 2024年 / 16卷 / 06期

关键词：

ChatGPT; LLMs; software engineering; software requirements; generative AI;

D O I：

10.3390/fi16060180

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Large language models (LLMs) have had a significant impact on several domains, including software engineering. However, a comprehensive understanding of LLMs' use, impact, and potential limitations in software engineering is still emerging and remains in its early stages. This paper analyzes the role of large language models (LLMs), such as ChatGPT-3.5, in software requirements engineering, a critical area in software engineering experiencing rapid advances due to artificial intelligence (AI). By analyzing several studies, we systematically evaluate the integration of ChatGPT into software requirements engineering, focusing on its benefits, challenges, and ethical considerations. This evaluation is based on a comparative analysis that highlights ChatGPT's efficiency in eliciting requirements, accuracy in capturing user needs, potential to improve communication among stakeholders, and impact on the responsibilities of requirements engineers. The selected studies were analyzed for their insights into the effectiveness of ChatGPT, the importance of human feedback, prompt engineering techniques, technological limitations, and future research directions in using LLMs in software requirements engineering. This comprehensive analysis aims to provide a differentiated perspective on how ChatGPT can reshape software requirements engineering practices and provides strategic recommendations for leveraging ChatGPT to effectively improve the software requirements engineering process.

引用

页数：21

共 33 条

[11] Suitability of Google Scholar as a source of scientific information and as a source of data for scientific evaluation-Review of the Literature [J].

Halevi, Gali ;

Moed, Henk ;

Bar-Ilan, Judit .

JOURNAL OF INFORMETRICS, 2017, 11 (03) :823-834

[12]

Hariri W, 2024, Arxiv, DOI [arXiv:2304.02017, 10.48550/arxiv.2304.02017, DOI 10.48550/ARXIV.2304.02017]

[13]

Hrnemalm A., 2023, Masters Thesis

[14]

Kalla D., 2023, J. Emerg. Technol. Innov. Res, V10, ph84

[15]

Kutzner T., 2023, X Jornadas Iberoamericanas de Innovacion Educativa en el Ambito de las TIC y las TAC

[16]

Liu K., 2022, P IEEE 23 INT C INF

[17] Improving requirements completeness: automated assistance through large language models [J].

Luitel, Dipeeka ;

Hassani, Shabnam ;

Sabetzadeh, Mehrdad .

REQUIREMENTS ENGINEERING, 2024, 29 (01) :73-95

[18]

Marr B, A Short History of ChatGPT: How We Got to Where We Are Today

[19]

Nguyen-Duc A, 2023, Arxiv, DOI arXiv:2310.18648

[20]

Oswal J.U., 2024, P 2024 2 INT C INT D

← 1 2 3 4 →