An Empirical Study on Software Defect Prediction Using CodeBERT Model
Deep learning-based software defect prediction has been popular these days. Recently, the publishing of the CodeBERT model has made it possible to perform many software engineering tasks. We propose various CodeBERT models targeting software defect prediction, including CodeBERT-NT, CodeBERT-PS, Cod...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/11/4793 |
| _version_ | 1797532945644257280 |
|---|---|
| author | Cong Pan Minyan Lu Biao Xu |
| author_facet | Cong Pan Minyan Lu Biao Xu |
| author_sort | Cong Pan |
| collection | DOAJ |
| description | Deep learning-based software defect prediction has been popular these days. Recently, the publishing of the CodeBERT model has made it possible to perform many software engineering tasks. We propose various CodeBERT models targeting software defect prediction, including CodeBERT-NT, CodeBERT-PS, CodeBERT-PK, and CodeBERT-PT. We perform empirical studies using such models in cross-version and cross-project software defect prediction to investigate if using a neural language model like CodeBERT could improve prediction performance. We also investigate the effects of different prediction patterns in software defect prediction using CodeBERT models. The empirical results are further discussed. |
| first_indexed | 2024-03-10T11:07:33Z |
| format | Article |
| id | doaj.art-a2e5fc9440da416fba5cd905b3450863 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T11:07:33Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-a2e5fc9440da416fba5cd905b34508632023-11-21T21:02:19ZengMDPI AGApplied Sciences2076-34172021-05-011111479310.3390/app11114793An Empirical Study on Software Defect Prediction Using CodeBERT ModelCong Pan0Minyan Lu1Biao Xu2The Key Laboratory on Reliability and Environmental Engineering Technology, Beihang University, Beijing 100191, ChinaThe Key Laboratory on Reliability and Environmental Engineering Technology, Beihang University, Beijing 100191, ChinaThe Key Laboratory on Reliability and Environmental Engineering Technology, Beihang University, Beijing 100191, ChinaDeep learning-based software defect prediction has been popular these days. Recently, the publishing of the CodeBERT model has made it possible to perform many software engineering tasks. We propose various CodeBERT models targeting software defect prediction, including CodeBERT-NT, CodeBERT-PS, CodeBERT-PK, and CodeBERT-PT. We perform empirical studies using such models in cross-version and cross-project software defect prediction to investigate if using a neural language model like CodeBERT could improve prediction performance. We also investigate the effects of different prediction patterns in software defect prediction using CodeBERT models. The empirical results are further discussed.https://www.mdpi.com/2076-3417/11/11/4793software defect predictiondeep transfer learningpre-trained language modelsoftware reliability |
| spellingShingle | Cong Pan Minyan Lu Biao Xu An Empirical Study on Software Defect Prediction Using CodeBERT Model Applied Sciences software defect prediction deep transfer learning pre-trained language model software reliability |
| title | An Empirical Study on Software Defect Prediction Using CodeBERT Model |
| title_full | An Empirical Study on Software Defect Prediction Using CodeBERT Model |
| title_fullStr | An Empirical Study on Software Defect Prediction Using CodeBERT Model |
| title_full_unstemmed | An Empirical Study on Software Defect Prediction Using CodeBERT Model |
| title_short | An Empirical Study on Software Defect Prediction Using CodeBERT Model |
| title_sort | empirical study on software defect prediction using codebert model |
| topic | software defect prediction deep transfer learning pre-trained language model software reliability |
| url | https://www.mdpi.com/2076-3417/11/11/4793 |
| work_keys_str_mv | AT congpan anempiricalstudyonsoftwaredefectpredictionusingcodebertmodel AT minyanlu anempiricalstudyonsoftwaredefectpredictionusingcodebertmodel AT biaoxu anempiricalstudyonsoftwaredefectpredictionusingcodebertmodel AT congpan empiricalstudyonsoftwaredefectpredictionusingcodebertmodel AT minyanlu empiricalstudyonsoftwaredefectpredictionusingcodebertmodel AT biaoxu empiricalstudyonsoftwaredefectpredictionusingcodebertmodel |