Explanation Needs in App Reviews: Taxonomy and Automated Detection

TL;DR

This paper investigates users' explanation needs in app reviews, creating a taxonomy and developing automated methods to identify these needs, thereby aiding developers in improving explainability features.

Contribution

It introduces a taxonomy of explanation needs in app reviews and presents an effective classifier for automatic detection of these needs.

Findings

Best classifier achieves 86% F-score on unseen reviews

Manual coding of 1,730 reviews led to a comprehensive taxonomy

Automated detection can support eliciting explanation requirements

Abstract

Explainability, i.e. the ability of a system to explain its behavior to users, has become an important quality of software-intensive systems. Recent work has focused on methods for generating explanations for various algorithmic paradigms (e.g., machine learning, self-adaptive systems). There is relatively little work on what situations and types of behavior should be explained. There is also a lack of support for eliciting explainability requirements. In this work, we explore the need for explanation expressed by users in app reviews. We manually coded a set of 1,730 app reviews from 8 apps and derived a taxonomy of Explanation Needs. We also explore several approaches to automatically identify Explanation Needs in app reviews. Our best classifier identifies Explanation Needs in 486 unseen reviews of 4 different apps with a weighted F-score of 86%. Our work contributes to a better understanding of users' Explanation Needs. Automated tools can help engineers focus on these needs and ultimately elicit valid Explanation Needs.