Feature Learning via Correlation Analysis for Effective Duplicate Detection
Source abstract
Abstract
With the growing reliance on software, the frequency of software bugs has increased significantly. To address these issues, users or developers typically submit bug reports, which developers analyze and resolve. However, many submitted bug reports are duplicates of previously reported issues, creating inefficiencies in the bug resolution process. To enhance developer productivity, an automatic method for detecting duplicate bug reports is essential. In this study, we present a novel approach for identifying duplicate and nonduplicate bug reports using feature learning through correlation analysis. Our method utilizes bug report features, including product and component information, extracted from bug repositories. The process begins with preprocessing the bug reports to ensure data quality. Next, a feature selection algorithm identifies relevant features, which are then used to train a machine learning model based on bidirectional encoder representations from transformers (BERT). The proposed model’s effectiveness was evaluated across multiple datasets: Apache, JDT, Platform, KDE, Core, Firefox, and Thunderbird. Our results show detection accuracies of 91.41%, 88.66%, 86.08%, 92.94%, 90.68%, 88.25%, and 91.62%, respectively. These outcomes represent a significant improvement of 32% to 41% compared to baseline models, including convolutional neural networks (CNNs), long short-term memory networks (LSTMs), convolutional LSTMs (CNN-LSTMs), Naive Bayes classifiers, and random forest classifiers. Our findings show that the proposed model is highly effective for duplicate bug report prediction and offers substantial advancements over existing methods. This approach has the potential to streamline bug management processes and improve overall software development efficiency.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Machine Learning and Data Classification · Text and Document Classification Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Applied Mathematics (Computer System Institute), Hankyong National University, Anseong-si 17579, Republic of Korea
Department of Computer Applied Mathematics, Hankyong National University, Anseong-si 17579, Republic of Korea
Department of Computer Engineering, Kyungnam University, Changwon-si 51767, Republic of Korea
Funding
Hankyong National University
References (42)
Show source-provided references
1. Yang, G., Tao, Z., and Lee, B. (2014, January 21–25). Towards semi-automatic bug triage and severity prediction based on topic model and multi-feature of bug reports. Proceedings of the IEEE 38th Annual Computer Software and Applications Conference, Vasteras, Sweden.10.1109/COMPSAC.2014.16 ↗
2. (2023, January 19). Apache. Available online: https://bz.apache.org/bugzilla/.
3. Jalbert, N., and Weimer, W. (2008, January 24–27). Automated duplicate detection for bug tracking systems. Proceedings of the IEEE International Conference on Dependable Systems and Networks with FTCS and DCC (DSN), Anchorage, AK, USA.10.1109/DSN.2008.4630070 ↗
4. Budhiraja, A., Dutta, K., Shrivastava, M., and Reddy, R. (2018, January 14–17). Towards word embeddings for improved duplicate bug report retrieval in software repositories. Proceedings of the ACM SIGIR International Conference on Theory of Information Retrieval, Tianjin, China.10.1145/3234944.3234949 ↗
5. Lazar, A., Ritchey, S., and Sharif, B. (June, January 31). Improving the accuracy of duplicate bug report detection using textual similarity measures. Proceedings of the 11th Working Conference on Mining Software Repositories, Hyderabad, India.
6. A novel feature selection algorithm for text categorization10.1016/j.eswa.2006.04.001 ↗
7. Devlin, J., Chang, M.W., Lee, K., and Toutanova, K. (2018). BERT: Pre-training of deep bidirectional transformers for language under-standing. arXiv.
8. Gravetter, F.J., and Wallnau, L.B. (2014). Introduction to the t statistic. Essentials of Statistics for the Behavioral Sciences, Cengage Learning. [8th ed.].
9. Woolson, R.F. (2007). Wilcoxon signed-rank test. Wiley Encyclopedia of Clinical Trials, Wiley.10.1002/9780471462422.eoct979 ↗
10. Shapiro–Wilk test with known mean
11. Zhang, T., Wu, F., Katiyar, A., Weinberger, K.Q., and Artzi, Y. (2020). Revisiting few-sample BERT fine-tuning. arXiv.
12. Sun, C., Lo, D., Khoo, S.-C., and Jiang, J. (2011, January 6–10). Towards more accurate retrieval of duplicate bug reports. Proceedings of the 26th IEEE/ACM International Conference on Automated Software Engineering (ASE), Lawrence, KS, USA.10.1109/ASE.2011.6100061 ↗
13. Murphy, G.C., and Cubranic, D. (2004, January 20–25). Automatic bug triage using text categorization. Proceedings of the Sixteenth International Conference on Software Engineering & Knowledge Engineering (SEKE), Banff, Canada.
14. He, J., Xu, L., Yan, M., Xia, X., and Lei, Y. (2020, January 13–15). Duplicate bug report detection using dual-channel convolutional neural networks. Proceedings of the 28th International Conference on Program Comprehension (ICPC), Seoul, Republic of Korea.10.1145/3387904.3389263 ↗
15. Parallel cleaning algorithm for similar duplicate Chinese data based on BERT
16. Sun, C., Qiu, X., Xu, Y., and Huang, X. (2019, January 18–20). How to fine-tune BERT for text classification?. Proceedings of the China National Con-ference on Chinese Computational Linguistics, Kunming, China.10.1007/978-3-030-32381-3_16 ↗
17. Gopalan, R.P., and Krishna, A. (2014, January 7–10). Duplicate bug report detection using clustering. Proceedings of the 23rd Australian Software Engineering Conference (ASWEC), Milsons Point, NSW, Australia.10.1109/ASWEC.2014.31 ↗
18. Lerch, J., and Mezini, M. (2013, January 5–8). Finding duplicates of your yet unwritten bug report. Proceedings of the 17th European Conference on Software Maintenance and Reengineering (CSMR), Genoa, Italy.10.1109/CSMR.2013.17 ↗
19. Sun, C., Lo, D., Wang, X., Jiang, J., and Khoo, S.-C. (2010, January 1–8). A discriminative model approach for accurate duplicate bug report retrieval. Proceedings of the 32nd ACM/IEEE International Conference on Software Engineering—Volume 1 (ICSE), Cape Town, South Africa.10.1145/1806799.1806811 ↗
20. Tian, Y., Sun, C., and Lo, D. (2012, January 27–30). Improved duplicate bug report identification. Proceedings of the 16th European Conference on Software Maintenance and Reengineering (CSMR), Szeged, Hungary.10.1109/CSMR.2012.48 ↗
21. Sureka, A., and Jalote, P. (December, January 30). Detecting duplicate bug reports using character n-gram-based features. Proceedings of the Asia Pacific Software Engineering Conference (APSEC), Sydney, Australia.
22. Banerjee, S., Cukic, B., and Adjeroh, D. (2012, January 25–27). Automated duplicate bug report classification using subsequence matching. Proceedings of the IEEE 14th International Symposium on High-Assurance Systems Engineering (HASE), Omaha, NE, USA.10.1109/HASE.2012.38 ↗
23. Duplicate bug report detection and classification system based on deep learning technique10.1109/ACCESS.2020.3033045 ↗
24. Automated duplicate bug report detection using multi-factor analysis10.1587/transinf.2016EDP7052 ↗
25. An HMM-based approach for automatic de-tection and classification of duplicate bug reports10.1016/j.infsof.2019.05.007 ↗
26. SiameseQAT: A semantic context-based duplicate bug report detection using replicated cluster information10.1109/ACCESS.2021.3066283 ↗
27. Akilan, T., Shah, D., Patel, N., and Mehta, R. (2020, January 11–14). Fast detection of duplicate bug reports using LDA-based topic modeling and classi-fication. Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC), Toronto, ON, Canada.10.1109/SMC42975.2020.9283289 ↗
28. (2023, January 19). Apache #39293. Available online: https://bz.apache.org/bugzilla/show_bug.cgi?id=39293.
29. (2023, January 19). Apache #2492. Available online: https://bz.apache.org/bugzilla/show_bug.cgi?id=2492.
30. (2023, January 19). Apache #3089. Available online: https://bz.apache.org/bugzilla/show_bug.cgi?id=3089.
31. Kao, A., and Poteet, S.R. (2007). Natural Language Processing and Text Mining, Springer Science & Business Media.10.1007/978-1-84628-754-1 ↗
32. (2023, January 19). JDT. Available online: https://bugs.eclipse.org/bugs/describecomponents.cgi?product=JDT.
33. (2023, January 19). Platform. Available online: https://bugs.eclipse.org/bugs/describecomponents.cgi?product=Platform.
34. (2023, January 19). KDE. Available online: https://bugs.kde.org/.
35. (2023, January 19). Core. Available online: https://bugzilla.mozilla.org/describecomponents.cgi?product=core.
36. (2023, January 19). Firefox. Available online: https://bugzilla.mozilla.org/describecomponents.cgi?product=firefox.
37. (2023, January 19). Thunderbird. Available online: https://bugzilla.mozilla.org/describecomponents.cgi?product=thunderbird.
38. Goutte, C., and Gaussier, E. (2005, January 21–23). A probabilistic interpretation of precision, recall and F-score, with implication for evaluation. Proceedings of the European Conference on Information Retrieval (ECIR), Santiago de Compostela, Spain.10.1007/978-3-540-31865-1_25 ↗
39. Zhou, J., Zhang, H., and Lo, D. (2012, January 2–9). Where should the bugs be fixed? More accurate information retrieval-based bug localization based on bug reports. Proceedings of the 34th International Conference on Software Engineering (ICSE), Zurich, Switzerland.10.1109/ICSE.2012.6227210 ↗
40. Kukkar, A., Mohana, R., Nayyar, A., Kim, J., Kang, B.G., and Chilamkurti, N. (2019). A novel deep-learning-based bug severity classifi-cation technique using convolutional neural networks and random forest with boosting. Sensors, 19.10.3390/s19132964 ↗
41. Zhang, J., Li, Y., Tian, J., and Li, T. (2018, January 12–14). LSTM-CNN hybrid model for text classification. Proceedings of the IEEE 3rd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), Chongqing, China.10.1109/IAEAC.2018.8577620 ↗
42. Sharma, M., Bedi, P., Chaturvedi, K.K., and Singh, V.B. (2012, January 27–29). Predicting the priority of a reported bug using machine learning techniques and cross-project validation. Proceedings of the 12th International Conference on Intelligent Systems Design and Appli-cations (ISDA), Kochi, India.10.1109/ISDA.2012.6416595 ↗