Automatic Generation of Explainability Requirements and Software Explanations From User Reviews

TL;DR

This paper presents an automated tool-supported approach to derive explainability requirements and generate explanations from user reviews, aiming to improve transparency and trust in software systems, with empirical evaluation and dataset release.

Contribution

It introduces a novel automated method for deriving explainability requirements and explanations from user feedback, supported by empirical validation and dataset sharing.

Findings

AI-generated explanations are often clearer and stylistically preferred.

AI requirements tend to lack relevance and correctness.

Human validation is crucial for ensuring correctness.

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.