Studying the explanations for the automated prediction of bug and non-bug issues using LIME and SHAP
Lists
Only you see this
Abstract
The identification of bugs within issues reported to an issue tracking system is crucial for triage. Machine learning models have shown promising results for this task. However, we have only limited knowledge of how such models identify bugs. Explainable AI methods like LIME and SHAP can be used to increase this knowledge.
BibTeX
@article{schulte2024studying,
author = {Lukas Schulte and Benjamin Ledel and Steffen Herbold},
title = {{Studying the explanations for the automated prediction of bug and non-bug issues using LIME and SHAP}},
journal = {Empir. Softw. eng},
year = {2024},
doi = {10.1007/s10664-024-10469-1},
}