Zur Hauptnavigation wechseln Zur Suche wechseln Zum Hauptinhalt wechseln

Automatic Generation of Explainability Requirements and Software Explanations From User Reviews

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Abstract

Explainability has become a crucial non-functional requirement to enhance transparency, build user trust, and ensure regulatory compliance. However, translating explanation needs expressed in user feedback into structured requirements and corresponding explanations remains challenging. While existing methods can identify explanation-related concerns in user reviews, there is no established approach for systematically deriving requirements and generating aligned explanations. To contribute toward addressing this gap, we introduce a tool-supported approach that automates this process. To evaluate its effectiveness, we collaborated with an industrial automation manufacturer to create a dataset of 58 user reviews, each annotated with manually crafted explainability requirements and explanations. Our evaluation shows that while AI-generated requirements often lack relevance and correctness compared to human-created ones, the AI-generated explanations are frequently preferred for their clarity and style. Nonetheless, correctness remains an issue, highlighting the importance of human validation. This work contributes to the advancement of explainability requirements in software systems by (1) introducing an automated approach to derive requirements from user reviews and generate corresponding explanations, (2) providing empirical insights into the strengths and limitations of automatically generated artifacts, and (3) releasing a curated dataset to support future research on the automatic generation of explainability requirements.

OriginalspracheEnglisch
Titel des SammelwerksProceedings - 2025 IEEE 33rd International Requirements Engineering Conference Workshops, REW 2025
Herausgeber (Verlag)Institute of Electrical and Electronics Engineers Inc.
Seiten49-58
Seitenumfang10
ISBN (elektronisch)9798331538347
ISBN (Print)979-8-3315-3835-4
DOIs
PublikationsstatusVeröffentlicht - 1 Sept. 2025
Veranstaltung33rd IEEE International Requirements Engineering Conference Workshops, REW 2025 - Valencia, Spanien
Dauer: 1 Sept. 20255 Sept. 2025

Publikationsreihe

NameProceedings - IEEE International Requirements Engineering Conference Workshops
ISSN (Print)2770-6826
ISSN (elektronisch)2770-6834

Konferenz

Konferenz33rd IEEE International Requirements Engineering Conference Workshops, REW 2025
KurztitelREW 2025
Land/GebietSpanien
OrtValencia
Zeitraum1 Sept. 20255 Sept. 2025

ASJC Scopus Sachgebiete

  • Artificial intelligence
  • Software
  • Sicherheit, Risiko, Zuverlässigkeit und Qualität
  • Modellierung und Simulation

Dieses zitieren