A Conceptual Framework for Explainability Requirements in Software-Intensive Systems

Software-intensive systems include enterprise systems, IoT systems, cyber-physical systems, and industrial control systems where software plays a vital role. In such systems, the software is increasingly responsible for autonomous decision-making. However, trust can be hindered by the black-box natu...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE International Requirements Engineering Conference Workshops (Online) S. 309 - 315
Hauptverfasser: Bersani, Marcello M., Camilli, Matteo, Lestingi, Livia, Mirandola, Raffaela, Rossi, Matteo, Scandurra, Patrizia
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.09.2023
Schlagworte:
Decision making
Explainability
explainability requirements
explainable software systems
Human-machine systems
Industrial control
Measurement
Production
Service robots
Shape
ISSN:2770-6834
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Software-intensive systems include enterprise systems, IoT systems, cyber-physical systems, and industrial control systems where software plays a vital role. In such systems, the software is increasingly responsible for autonomous decision-making. However, trust can be hindered by the black-box nature of these systems, whose autonomous decisions may be confusing or even dangerous for humans. Thus, explainability emerges as a crucial non-functional property to achieve transparency and increase the understanding of the systems' behavior, fostering their acceptance in our society. This paper introduces a conceptual framework for eliciting explainability requirements at different granularity levels. Each level is associated with a set of meta-requirements and means for instantiating the framework within a system to make it capable of producing explanations in a given application domain. We illustrate our conceptual framework using a running example from the robotics domain.
ISSN:2770-6834
DOI:10.1109/REW57809.2023.00059