mlsanityData to 7 Oct 2026

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

arXiv 2209.07623 ↗First posted 15 Sep 2022cs.SE cs.LGcited by 4

Not on the map. Why?

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.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 19 of its 45 references that are in the map. First posted on arXiv 15 Sep 2022.

Builds on

19 of 45 references.

References · 19

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2016Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answeringcited by 2,498
  5. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  6. 2019Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methodscited by 440
  7. 2018On the Robustness of Interpretability Methodscited by 310
  8. 2016Model-Agnostic Interpretability of Machine Learningcited by 219
  9. 2020Statistical stability indices for LIME: obtaining reliable explanations for Machine Learning modelscited by 40
  10. 2020An Explainable Machine Learning Model for Early Detection of Parkinson's Disease using LIME on DaTscan Imagerycited by 25
  11. 2020Looking Deeper into Tabular LIMEcited by 20
  12. 2020Predicting Defective Lines Using a Model-Agnostic Techniquecited by 14
7 more
  1. 2021On the validity of pre-trained transformers for natural language processing in the software engineering domaincited by 11
  2. 2021Practitioners' Perceptions of the Goals and Visual Explanations of Defect Prediction Modelscited by 9
  3. 2020Explainable AI for Software Engineeringcited by 8
  4. 2019Problems with SZZ and Features: An empirical study of the state of practice of defect prediction data collectioncited by 6
  5. 2020On the feasibility of automated prediction of bug and non-bug issuescited by 6
  6. 2019Learning to Identify Security-Related Issues Using Convolutional Neural Networkscited by 4
  7. 2022Predicting Issue Types with seBERTcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 1; 2026: 1.

4 papers.

  1. 2024Machine learning approaches for automatic defect detection in photovoltaic systemscited by 0
  2. 2024Automated Trustworthiness Oracle Generation for Machine Learning Text Classifierscited by 0
  3. 2025Feature Attribution in 5G Intrusion Detection: A Statistical vs. Logic-Based Comparisoncited by 0
  4. 2026Towards Explainable Stakeholder-Aware Requirements Prioritisation in Aged-Care Digital Healthcited by 0