Mapping Artificial Intelligence Applications in Requirements Engineering: A CiteSpace-Based Bibliometric Review

DOI: https://doi.org/10.62517/jike.202604320

Author(s)

Guoxin Lin1,2,3, Ronghai Wang1,2,3,*, Hongwei Wang1,2,3, Fen Cai1,2,3

Affiliation(s)

1School of Mathematics and Computer Science, Quanzhou Normal University, Quanzhou, China 2Fujian Provincial Key Laboratory of Data Intensive Computing, Quanzhou, China 3Key Laboratory of Intelligent Computing and Information Processing, Quanzhou, China *Corresponding Author

Abstract

Artificial intelligence (AI) and requirements engineering (RE) intersect in two related research streams. One applies AI methods to RE tasks, whereas the other adapts RE practices to the particular demands of AI-enabled systems. This study maps the development of both streams and examines how their evidence bases connect. A search of the Web of Science Core Collection returned 1,021 articles published between 1 January 2000 and 31 July 2026. Screening of the bibliographic fields excluded 897 off-topic records, one retracted article, and two articles with an Expression of Concern. The remaining 121 records were analyzed with CiteSpace 6.4.R2. The analyses covered keyword co-occurrence and clustering, thematic timelines, citation bursts, reference co-citation, and country collaboration; representative records were also checked manually. The keyword network contained 240 nodes and 695 links. Seven main themes were identified: AI-assisted requirements analysis, RE for AI systems and quality assurance, LLM-assisted automation, systems design, elicitation and inconsistency detection, human-centered explainability, and AI-based modeling. The reference co-citation network contained 911 nodes and 952 links, but only 16% of its nodes belonged to the largest connected component. Under the primary setting, no keyword maintained a burst for two years. A separate one-year sensitivity analysis identified a burst for large language models from 2025 to 2026. Overall, the mapped literature has recently moved beyond task-specific NLP and ML toward generative and agentic workflows. Industrial validation and traceability, however, remain limited, and lifecycle governance and human oversight have not yet been adequately resolved.

Keywords

Artificial Intelligence; Requirements Engineering; AI4RE; RE4AI; Citespace; Bibliometric Analysis; Large Language Models

References

[1] Zhao L, Alhoshan W, Ferrari A, Letsholo KJ, Ajagbe MA, Chioasca EV, Batista-Navarro RT. Natural Language Processing for Requirements Engineering: A Systematic Mapping Study. ACM Computing Surveys, 2021, 54(3): Article 55, 1-41. [2] Sharma A, Tripathi AK. Evaluating user story quality with LLMs: a comparative study. Journal of Intelligent Information Systems, 2025, 63(4): 1423-1451. [3] Massoudi S, Fuge M. Agentic Large Language Models for Conceptual Systems Engineering and Design. Journal of Mechanical Design, 2026, 148(5): 051405. [4] Cheng H, Husen JH, Lu Y, Racharak T, Yoshioka N, Ubayashi N, Washizaki H. Generative AI for Requirements Engineering: A Systematic Literature Review. Software: Practice and Experience, 2026, 56(2): 141-170. [5] Ahmad K, Abdelrazek M, Arora C, Bano M, Grundy J. Requirements engineering for artificial intelligence systems: A systematic mapping study. Information and Software Technology, 2023, 158: 107176. [6] Martínez-Fernández S, Bogner J, Franch X, Oriol M, Siebert J, Trendowicz A, Vollmer AM, Wagner S. Software Engineering for AI-Based Systems: A Survey. ACM Transactions on Software Engineering and Methodology, 2022, 31(2): Article 37, 1-59. [7] Al Ghanmi H, Bahsoon R. ExplanaSC: A Framework for Determining Information Requirements for Explainable Blockchain Smart Contracts. IEEE Transactions on Software Engineering, 2024, 50(8): 1984-2004. [8] Chen C. CiteSpace II: Detecting and visualizing emerging trends and transient patterns in scientific literature. Journal of the American Society for Information Science and Technology, 2006, 57(3): 359-377. [9] Chen C. Science mapping: A systematic review of the literature. Journal of Data and Information Science, 2017, 2(2): 1-40. [10] Alhoshan W, Ferrari A, Zhao L. Zero-shot learning for requirements classification: An exploratory study. Information and Software Technology, 2023, 159: 107202. [11] Khan JA, Liu L, Wen L. Requirements knowledge acquisition from online user forums. IET Software, 2020, 14(3): 242-253. [12] Gärtner AE, Göhlich D. Automated requirement contradiction detection through formal logic and LLMs. Automated Software Engineering, 2024, 31(2): 49. [13] Saini R, Mussbacher G, Guo JLC, Kienzle J. Automated, interactive, and traceable domain modelling empowered by artificial intelligence. Software and Systems Modeling, 2022, 21(3): 1015-1045. [14] Kurtanović Z, Maalej W. Automatically Classifying Functional and Non-functional Requirements Using Supervised Machine Learning. 2017 IEEE 25th International Requirements Engineering Conference, 2017: 490-495. [15] Ambriola V, Gervasi V. On the Systematic Analysis of Natural Language Requirements with CIRCE. Automated Software Engineering, 2006, 13(1): 107-167.