EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Extending the Comparative Study of Anomaly Detection Tools in Software Requirements with ChatGPT

Fábio Rodrigues Pereira, Heitor Augustus Xavier Costa, Paulo Afonso Parreira Júnior

Journal of Software Engineering Research and Development · 08.05.2026 · 14 (1) · 88-102

DOI: 10.5753/jserd.2026.5919 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Software Engineering Research and Development, online erschienen am 08.05.2026. Verfasst von Fábio Rodrigues Pereira und 2 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A software requirement indicates a capability or characteristic that a software system must possess to provide value to its stakeholders. It is essential to ensure that the description of the requirements is unambiguous to allow for proper understanding and facilitate its evolution. However, since most software requirements are described in natural language, they may contain subjectivity and inconsistencies in their descriptions, which are conventionally referred to as "Software Requirements Anomalies". Several studies propose tools to aid in the detection of requirements anomalies. However, it can be observed that few of these studies evaluate the effectiveness (recall and precision) of the proposed tools. Therefore, this work presents a comparative study of three anomaly detection tools (RETA, Tactile Check, and Tiger Pro), as well as the ChatGPT model, analyzed based on requirements documents from different domains containing over 85 anomalies. The results show that the Tactile Check tool produced the best performance. Although ChatGPT offers advantages in terms of information visualization and flexibility of interaction, its performance was not satisfactory compared to tools specifically designed for anomaly detection in software requirements. All analyzed tools, including ChatGPT, demonstrated unsatisfactory levels of recall and precision, averaging below 66% and 57%, respectively. These results highlight the need for further contributions in this research area.

Zitieren

APA

Pereira, F. R., Costa, H. A. X., & Júnior, P. A. P. (2026). Extending the Comparative Study of Anomaly Detection Tools in Software Requirements with ChatGPT. Journal of Software Engineering Research and Development, 14(1), 88-102. https://doi.org/10.5753/jserd.2026.5919

Vancouver

Pereira FR, Costa HAX, Júnior PAP. Extending the Comparative Study of Anomaly Detection Tools in Software Requirements with ChatGPT. Journal of Software Engineering Research and Development. 2026;14(1):88-102. doi:10.5753/jserd.2026.5919

BibTeX
@article{Pereira2026,
  author = {Pereira, Fábio Rodrigues and Costa, Heitor Augustus Xavier and Júnior, Paulo Afonso Parreira},
  title = {Extending the Comparative Study of Anomaly Detection Tools in Software Requirements with ChatGPT},
  journal = {Journal of Software Engineering Research and Development},
  year = {2026},
  volume = {14},
  number = {1},
  pages = {88--102},
  doi = {10.5753/jserd.2026.5919}
}
Kostenlos starten →