# Studying the explanations for the automated prediction of bug and non-bug issues using LIME and SHAP

arXiv: https://arxiv.org/abs/2209.07623 · HTML: https://mlsanity.com/paper/2209.07623/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 45 references that are in the map.
- First posted on arXiv 15 Sep 2022.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods](https://mlsanity.com/paper/1911.02508/) (2019)
- [On the Robustness of Interpretability Methods](https://mlsanity.com/paper/1806.08049/) (2018)
- [Model-Agnostic Interpretability of Machine Learning](https://mlsanity.com/paper/1606.05386/) (2016)
- [Statistical stability indices for LIME: obtaining reliable explanations for Machine Learning models](https://mlsanity.com/paper/2001.11757/) (2020)
- [An Explainable Machine Learning Model for Early Detection of Parkinson's Disease using LIME on DaTscan Imagery](https://mlsanity.com/paper/2008.00238/) (2020)
- [Looking Deeper into Tabular LIME](https://mlsanity.com/paper/2008.11092/) (2020)
- [Predicting Defective Lines Using a Model-Agnostic Technique](https://mlsanity.com/paper/2009.03612/) (2020)
- [On the validity of pre-trained transformers for natural language processing in the software engineering domain](https://mlsanity.com/paper/2109.04738/) (2021)
- [Practitioners' Perceptions of the Goals and Visual Explanations of Defect Prediction Models](https://mlsanity.com/paper/2102.12007/) (2021)
- [Explainable AI for Software Engineering](https://mlsanity.com/paper/2012.01614/) (2020)
- [Problems with SZZ and Features: An empirical study of the state of practice of defect prediction data collection](https://mlsanity.com/paper/1911.08938/) (2019)
- [On the feasibility of automated prediction of bug and non-bug issues](https://mlsanity.com/paper/2003.05357/) (2020)
- [Learning to Identify Security-Related Issues Using Convolutional Neural Networks](https://mlsanity.com/paper/1908.00614/) (2019)
- [Predicting Issue Types with seBERT](https://mlsanity.com/paper/2205.01335/) (2022)

## Built on by (most cited first, 4 of 4)

- [Machine learning approaches for automatic defect detection in photovoltaic systems](https://mlsanity.com/paper/2409.16069/) (2024)
- [Automated Trustworthiness Oracle Generation for Machine Learning Text Classifiers](https://mlsanity.com/paper/2410.22663/) (2024)
- [Feature Attribution in 5G Intrusion Detection: A Statistical vs. Logic-Based Comparison](https://mlsanity.com/paper/2509.10206/) (2025)
- [Towards Explainable Stakeholder-Aware Requirements Prioritisation in Aged-Care Digital Health](https://mlsanity.com/paper/2603.29114/) (2026)

## Abstract (arXiv)

Context: The identification of bugs within the reported issues in an issue tracker is crucial for the triage of issues. Machine learning models have shown promising results regarding the performance of automated issue type prediction. However, we have only limited knowledge beyond our assumptions how such models identify bugs. LIME and SHAP are popular technique to explain the predictions of classifiers. Objective: We want to understand if machine learning models provide explanations for the classification that are reasonable to us as humans and align with our assumptions of what the models should learn. We also want to know if the prediction quality is correlated with the quality of explanations. Method: We conduct a study where we rate LIME and SHAP explanations based on their quality of explaining the outcome of an issue type prediction model. For this, we rate the quality of the explanations themselves, i.e., if they align with our expectations and if they help us to understand the underlying machine learning model.