Abstract
AI in Requirements Engineering (RE) relies on industrial data, yet safety and privacy risks limit its use. While the GDPR distinguishes only between anonymization and pseudonymization, we use neutralization as a semantics-preserving technique. In AI-supported RE, data heterogeneity and cross-domain variability impede model training. We propose guidelines for semantics-preserving preprocessing for RE datasets based on ISO 29148 criteria, showing that neutralization does not compromise semantics. The approach enables industry-academia collaboration through AI-assisted RE in product development.
| Original language | English |
|---|---|
| Journal | Proceedings of the Design Society |
| Volume | 6 |
| Pages (from-to) | 807-816 |
| Number of pages | 10 |
| DOIs | |
| Publication status | Published - 08.2026 |
| Event | 19th International Design Conference - DESIGN 2026 - Dubrovnik, Croatia Duration: 18.05.2026 → 26.05.2026 Conference number: 19 https://www.designconference.org/ |
Bibliographical note
Publisher Copyright:© The Author(s), 2026.
UN SDGs
This output contributes to the following UN Sustainable Development Goals (SDGs)
-
SDG 8 Decent Work and Economic Growth -
SDG 9 Industry, Innovation, and Infrastructure
Research areas and keywords
- Informatics
- requirements management
- artificial intelligence (AI)
- neutralisation
- ISO 29148
- data‑driven design
- Engineering
ASJC Scopus Subject Areas
- Software
- Modelling and Simulation
- Computer Science Applications
- Computer Graphics and Computer-Aided Design
Fingerprint
Dive into the research topics of 'ISOprep: an LLM-driven pipeline for semantics-preserving processing of neutralized requirements according to ISO 29148'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver