Automatic Generation of Explainability Requirements and Software Explanations From User Reviews

July 10, 2025 Β· Declared Dead Β· πŸ› 2025 IEEE 33rd International Requirements Engineering Conference Workshops (REW)

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Martin Obaidi, Jannik Fischbach, Jakob Droste, Hannah Deters, Marc Herrmann, Jil KlΓΌnder, Steffen KrΓ€tzig, Hugo Villamizar, Kurt Schneider arXiv ID 2507.07344 Category cs.SE: Software Engineering Citations 3 Venue 2025 IEEE 33rd International Requirements Engineering Conference Workshops (REW) Last Checked 4 months ago
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.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Software Engineering

Died the same way β€” πŸ‘» Ghosted