The Impact of Mislabelling on the Performance and Interpretation of Defect Prediction Models
Open accessThe DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
The reliability of a prediction model depends on the quality of the data from which it was trained. Therefore, defect prediction models may be unreliable if they are trained using noisy data. Recent research suggests that randomly-injected noise that changes the classification (label) of software modules from defective to clean (and vice versa) can impact the performance of defect models. Yet, in reality, incorrectly labelled (i.e., mislabelled) issue reports are likely non-random. In this paper, we study whether mislabelling is random, and the impact that realistic mislabelling has on the performance and interpretation of defect models. Through a case study of 3,931 manually-curated issue reports from the Apache Jackrabbit and Lucene systems, we find that: (1) issue report mislabelling is not random; (2) precision is rarely impacted by mislabelled issue reports, suggesting that practitioners can rely on the accuracy of modules labelled as defective by models that are trained using noisy data; (3) however, models trained on noisy data typically achieve 56%-68% of the recall of models trained on clean data; and (4) only the metrics in top influence rank of our defect models are robust to the noise introduced by mislabelling, suggesting that the less influential metrics of models that are trained on noisy data should not be interpreted or used to make decisions.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
A Systematic Literature Review on Fault Prediction Performance in Software Engineering
Hall, T., Beecham, S., Bowes, D., Gray, D., & Counsell, S. (2012) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2011.103 · Cited by 1,154 · cited 1×
“The Impact of Mislabelling on the Performance and Interpretation of Defect Prediction Models Chakkrit Tantithamthavorn , Shane McIntosh , Ahmed E. Hassan , Akinori Ihara , Kenichi Matsumoto Graduate School of Information Science, Nara Institute of Science and Technology, Japan.”
MethodAn exploratory study of the pull-based software development model
Gousios, G., Pinzger, M., & Deursen, A. V. (2014) · Proceedings of the 36th International Conference on Software Engineering · doi:10.1145/2568225.2568260 · Cited by 628 · cited 2×
“Although prior studies have also used random forest [13, 14, 22, 24, 28], our findings are entirely bound to this technique.”
MethodResult
Cited by
Automatically learning semantic features for defect prediction
Wang, S., Liu, T., & Tan, L. (2016) · Proceedings of the 38th International Conference on Software Engineering · doi:10.1145/2884781.2884804 · Cited by 689
An Empirical Comparison of Model Validation Techniques for Defect Prediction Models
Tantithamthavorn, C., McIntosh, S., Hassan, A. E., & Matsumoto, K. (2017) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2016.2584050 · Cited by 574
Self-citationThe Impact of Automated Parameter Optimization on Defect Prediction Models
Tantithamthavorn, C., McIntosh, S., Hassan, A. E., & Matsumoto, K. (2019) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2018.2794977 · Cited by 415
Self-citationLineVul: a transformer-based line-level vulnerability prediction
Fu, M., & Tantithamthavorn, C. (2022) · Proceedings of the 19th International Conference on Mining Software Repositories · doi:10.1145/3524842.3528452 · Cited by 384
Self-citationAutomated parameter optimization of classification techniques for defect prediction models
Tantithamthavorn, C., McIntosh, S., Hassan, A. E., & Matsumoto, K. (2016) · Proceedings of the 38th International Conference on Software Engineering · doi:10.1145/2884781.2884857 · Cited by 331
Self-citation
Metadata
- Authors
- Tantithamthavorn, C., McIntosh, S., Hassan, A. E., Ihara, A., & Matsumoto, K.
- Venue
- 2015 IEEE/ACM 37th IEEE International Conference on Software Engineering
- Publisher
- IEEE
- Published
- 2015-05
- Pages
- 812-823
- ISSN
- 0270-5257 (ISSN-L)
- OpenAlex
- W4243379839
- Cited by
- 140
- References
- 3
- FWCI
- 11.40
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.