SEAICYDec 3, 2020

Explainable AI for Software Engineering

arXiv:2012.01614v178 citations
AI Analysis

This paper highlights the need for explainable AI for software engineers to improve the adoption of AI/ML models in software engineering practices.

This paper addresses the impracticality, lack of explainability, and actionability of AI/ML models in software engineering. It summarizes three case studies demonstrating how explainable AI techniques can make software defect prediction models more practical, explainable, and actionable.

Artificial Intelligence/Machine Learning techniques have been widely used in software engineering to improve developer productivity, the quality of software systems, and decision-making. However, such AI/ML models for software engineering are still impractical, not explainable, and not actionable. These concerns often hinder the adoption of AI/ML models in software engineering practices. In this article, we first highlight the need for explainable AI in software engineering. Then, we summarize three successful case studies on how explainable AI techniques can be used to address the aforementioned challenges by making software defect prediction models more practical, explainable, and actionable.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes