1. An Empirical Study of Model-Agnostics Techniques for Defect Prediction Models.
    Jirayus Jiarpakdee, Chakkrit Tantithamthavorn, Hoa Khanh Dam, John Grundy, IEEE Transactions on Software Engineering (TSE).
    (One-line Abstract): This paper suggested to use LIME to explain the predictions of defect models, enabling managers to make data-informed decisions when developing software quality improvement plans. The results show that 65% of the practitioners agree that LIME is useful to help them understand why a file is predicted as defective.
    Preprint
  2. Deep Learning for Android Malware Defenses: a Systematic Literature Review.
    Yue Liu, Chakkrit Tantithamthavorn, Li Li, Yepang Liu, ACM Computing Survey. Impact Factor 10.282

  3. DeepLineDP: Towards a Deep Learning Approach for Line-Level Defect Prediction.
    Chanathip Pornprasit, Chakkrit Tantithamthavorn, IEEE Transactions on Software Engineering (TSE).
    Preprint | DOI | Replication Package
  4. GPT2SP: A Transformer-Based Agile Story Point Estimation Approach.
    Michael Fu, Chakkrit Tantithamthavorn, IEEE Transactions on Software Engineering (TSE).
    (One-line Abstract): This paper propose a GPT2-based Agile Story Point Estimation that achieves a median MAE of 1, which is more accurate than SOTA by 35%-57%, making our approach becomes the world most accurate story point estimation.
    Preprint | DOI
  5. Predicting Defective Lines Using a Model-Agnostic Technique.
    Supatsara Wattanakriengkrai, Patanamon Thongtanunam, Chakkrit Tantithamthavorn, Hideaki Hata, and Kenichi Matsumoto, IEEE Transactions on Software Engineering (TSE).
    (One-line Abstract): This paper is the first to propose line-level defect prediction, by using Explainable AI techniques to help developers understand which lines are likely to be defective in the future.
    Preprint | DOI | Replication Package
  6. SQAPlanner: Generating Data-informed Software Quality Improvement Plans.
    Dilini Rajapaksha, Chakkrit Tantithamthavorn, Jirayus Jiarpakdee, Christoph Bergmeir, John Grundy, and Wray Buntine, IEEE Transactions on Software Engineering (TSE).
    (One-line Abstract): This paper is the first to propose explainable defect prediction, by using Explainable AI techniques to help developers to better guide what to do and what not to do to improve software quality. 80% of the participants also found that our novel visualisation is more actionable than Microsoft’s Code Defect AI (the state-of-the-art approach).
    Preprint | DOI | Replication Package
  7. Search-Based Fairness Testing for Regression-Based Machine Learning Systems.
    Anjana Perera, Aldeida Aleti, Chakkrit Tantithamthavorn, Jirayus Jiarpakdee, Burak Turhan, Lisa Kuhn, Katie Walker, Empirical Software Engineering (EMSE).
    (One-line Abstract): This paper proposed a novel search-based fairness testing approach to discover discrimination bias in ED wait-time prediction systems.

  8. The Impact of Data Merging on the Interpretation of Cross-Project Just-In-Time Defect Models.
    Dayi Lin, Chakkrit Tantithamthavorn, Ahmed E. Hassan, IEEE Transactions on Software Engineering (TSE).
    Preprint | DOI
  9. AutoComment: A Simpler, Faster, More Accurate Code Review Comments Recommendation.
    Yang Hong, Chakkrit Tantithamthavorn, Patanamon Thongtanunam, Aldeida Aleti, In Proceedings of the Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE). Acceptance Rate 22% (99/449)

  10. AutoTransform: Towards Automated Code Transformation to Support Modern Code Review Process.
    Patanamon Thongtanunam, Chanathip Pornprasit, Chakkrit Tantithamthavorn, In Proceedings of the International Conference on Software Engineering (ICSE). Acceptance Rate: 197/751 (26%)
    Preprint | Replication Package
  11. LineVul: A Transformer-based Line-Level Vulnerability Prediction.
    Michael Fu, Chakkrit Tantithamthavorn, In Proceedings of the International Conference on Mining Software Repositories (MSR). Acceptance Rate: 45/138 (34%)
    (One-line Abstract): Our LineVul is able to accurately (75%-100% accuracy) discover vulnerabilities as many as 348 safety-critical Free Open-Source Software (FOSS) systems. These vulnerabilities are considered as the Top-25 most dangerous CWE types in 2021 (e.g., CWE-190 Integer Overflow, CWE-787 Out of bound Write, CWE-20 Improper Input Validation). These findings demonstrate the strong potential impact of our LineVul in real-world practices, providing a world-most accurate vulnerability discovery approach to help security analysts to discover vulnerabilities faster, enabling FOSS organizing teams to immediately react to the cyber attacks, and protecting cyber attacks from national and international's cyberinfrastructure.
    Preprint
  12. VulRepair: A T5-based Automated Software Vulnerability Repair.
    Micheal Fu, Chakkrit Tantithamthavorn, Trung Le, Van Nguyen, Dinh Phung, In Proceedings of the Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE). Acceptance Rate 22% (99/449)

  13. Where Should I Look at? Recommending Lines that Reviewers Should Pay Attention To.
    Yang Hong, Chakkrit Tantithamthavorn, Patanamon Thongtanunam, In Proceedings of the International Conference on Software Analysis, Evolution and Reengineering (SANER). Acceptance Rate: 72/199 (36.2%)
    (One-line Abstract): This paper proposed an approach to help reviewers pinpoint the lines that need some attentions, reducing reviewing effort to review in a smaller set of lines, and increasing the code review speed and reviewers' productivity.
    Preprint | Replication Package
  14. Actionable Analytics: Stop Telling Me What It Is; Please Tell Me What To Do.
    Chakkrit Tantithamthavorn, Jirayus Jiarpakdee, and John Grundy, IEEE Software.
    (One-line Abstract): This article, published at IEEE Software, which is a premier magazine in software engineering, summarising three successful case studies of how Explainable AI techniques can be used to make defect prediction models more practical, explainable, and actionable.
    | DOI
  15. Emergency medicine patient wait time multivariable prediction models: a multicentre derivation and validation study.
    Katie J Walker, Jirayus Jiarpakdee, Anne Loupis, Chakkrit Tantithamthavorn, Keith Joe, Michael Ben-Meir, Hamed Akhlaghi, Jennie Hutton, Wei Wang, Michael Stephenson, Gabriel Blecher, Paul Buntine, Amy Sweeny, Burak Turhan, Emergency Medicine Journal.
    Preprint | DOI
  16. Predicting Ambulance Patient Wait Times: A Multicenter Derivation and Validation Study.
    Katie J Walker, Jirayus Jiarpakdee, Anne Loupis, Chakkrit Tantithamthavorn, Keith Joe, Michael Ben-Meir, Hamed Akhlaghi, Jennie Hutton, Wei Wang, Michael Stephenson, Gabriel Blecher, Paul Buntine, Amy Sweeny, Burak Turhan, Annals of Emergency Medicine.
    Preprint | DOI
  17. The Impact of Correlated Metrics on the Interpretation of Defect Models.
    Jirayus Jiarpakdee, Chakkrit Tantithamthavorn, Ahmed Hassan, IEEE Transactions on Software Engineering (TSE).
    (One-line Abstract): This paper suggested to handle colliniearity and multicollinearity when interpreting defect prediction models (i.e., understanding what are the most important variables).
    Preprint | DOI
  18. (Tutorial) Explainable AI for Software Engineering.
    Chakkrit Tantithamthavorn, Jirayus Jiarpakdee, In Proceedings of the International Conference on Automated Software Engineering (ASE).
    (One-line Abstract): This is the world-first online book on the novel research topic of Explainable AI for Software Engineering. Within 24 hours after its release, the book has attracted more than 10,000+ page views from 29 countries. The book also was mentioned by the tweets from Australia Research Council, Digital Innovation Futures Victoria.
    Preprint | DOI | Code | Replication Package
  19. Assessing the Students Understanding and their Mistakes in Code Review Checklists--An Experience Report of 1,791 Code Review Checklists from 394 Students.
    Chun Yong Chong, Patanamon Thongtanunam, Chakkrit Tantithamthavorn, International Conference on Software Engineering: Joint Software Engineering Education and Training track (ICSE-JSEET).
    Preprint
  20. JITLine: A Simpler, Better, Faster, Finer-grained Just-In-Time Defect Prediction.
    Chanathip Pornprasit, Chakkrit Tantithamthavorn, In Proceedings of the International Conference on Mining Software Repositories (MSR).
    | Replication Package
  21. Practitioners Perceptions of the Goals and Visual Explanations of Defect Prediction Models.
    Jirayus Jiarpakdee, Chakkrit Tantithamthavorn, John Grundy, In Proceedings of the International Conference on Mining Software Repositories (MSR).
    Preprint
  22. PyExplainer: Explaining the Predictions of Just-In-Time Defect Models.
    Chanathip Pornprasit, Chakkrit Tantithamthavorn, Jirayus Jiarpakdee, Michael Fu, Patanamon Thongtanunam, In Proceedings of the International Conference on Automated Software Engineering (ASE). Acceptance Rate: 19% (82/427)
    ACM SIGSOFT Distinguished Paper Award
    Preprint | Code
  23. JITBot: An Explainable Just-In-Time Defect Prediction Bot.
    Chaiyakarn Khanan, Worawit Luewichana, Krissakorn Pruktharathikoon, Jirayus Jiarpakdee, Chakkrit Tantithamthavorn, Morakot Choetkiertikul, Chaiyong Ragkhitwetsagul, Thanwadee Sunetnanta, In Proceedings of the International Conference on Automated Software Engineering (ASE).
    Preprint
  24. Workload-Aware Reviewer Recommendation using a Multi-objective Search-Based Approach.
    Wisam Haitham Abbood Al-Zubaidi, Patanamon Thongtanunam, Hoa Khanh Dam, Chakkrit Tantithamthavorn, Aditya Ghose, In Proceedings of the International Conference on Predictive Modelling in Software Engineering (PROMISE).
    Preprint
  25. The Impact of Automated Feature Selection Techniques on the Interpretation of Defect Models.
    Jirayus Jiarpakdee, Chakkrit Tantithamthavorn, Christoph Treude, Empirical Software Engineering (EMSE).
    Preprint
  26. The Impact of Class Rebalancing Techniques on the Performance and Interpretation of Defect Prediction Models.
    Chakkrit Tantithamthavorn, Ahmed E. Hassan, Kenichi Matsumoto, IEEE Transactions on Software Engineering (TSE).
    (One-line Abstract): This paper suggested to consider using optimised SMOTE to improve the predictive accuracy, i.e., handling the class imbalance of the training datasets prior to training the defect models.
    Preprint | DOI
  27. Mining Software Defects: Should We Consider Affected Releases?.
    Suraj Yatish, Jirayus Jiarpakdee, Patanamon Thongtanunam, Chakkrit Tantithamthavorn, In Proceedings of the International Conference on Software Engineering (ICSE). Acceptance Rate: 21% (109/529)
    (One-line Abstract): This paper suggested using affected releases (i.e., the actual software releases that are affected) to label whether a file is considered to be defective or clean, instead of the assumptions of a post-release window period (i.e., any defects that are fixed after 6 months).
    Preprint
  28. The Impact of Automated Parameter Optimization on Defect Prediction Models.
    Chakkrit Tantithamthavorn, Shane McIntosh, Ahmed E. Hassan, Kenichi Matsumoto, IEEE Transactions on Software Engineering (TSE).
    Preprint | DOI
  29. An Experience Report on Defect Modelling in Practice: Pitfalls and Challenges.
    Chakkrit Tantithamthavorn and Ahmed E. Hassan, In Proceedings of the International Conference on Software Engineering: Software Engineering in Practice Track (ICSE-SEIP). Acceptance Rate: 24% (31/131)
    Preprint
  30. Artefact: An R Implementation of the AutoSpearman Function.
    Jirayus Jiarpakdee, Chakkrit Tantithamthavorn, Christoph Treude, In Proceedings of the International Conference on Software Maintenance and Evolution (ICSME).
    Preprint
  31. AutoSpearman: Automatically Mitigating Correlated Metrics for Interpreting Defect Models.
    Jirayus Jiarpakdee, Chakkrit Tantithamthavorn, Christoph Treude, In Proceedings of the International Conference on Software Maintenance and Evolution (ICSME). Acceptance Rate: 22% (37/174)
    (One-line Abstract): This paper suggested to avoid using existing automated feature selection techniques (e.g., Stepwise Regression) if the goal is to interpret defect prediction models, as they fail to mitigate correlated features and are dependent on random seeds.
    Preprint
  32. Studying the Dialogue Between Users and Developers of Free Apps in the Google Play Store.
    Safwat Hassan, Chakkrit Tantithamthavorn, Cor-Paul Bezemer, and Ahmed E. Hassan, Empirical Software Engineering (EMSE).
    Preprint
  33. The Impact of IR-based Classifier Configuration on the Performance and the Effort of Method-Level Bug Localization.
    Chakkrit Tantithamthavorn, Surafel Lemma Abebe, Ahmed E. Hassan, Akinori Ihara, and Kenichi Matsumoto, Information and Software Technology (IST).
    Preprint
  34. An Empirical Comparison of Model Validation Techniques for Defect Prediction Models.
    Chakkrit Tantithamthavorn, Shane McIntosh, Ahmed E. Hassan, Kenichi Matsumoto, IEEE Transactions on Software Engineering (TSE).
    (One-line Abstract): This paper suggested to use the Scott-Knott ESD test to identify the best classification techniques that are statistically significantly different with non-negligible Cliff's |delta| effect size. This paper also suggested to measure the accuracy of defect prediction models using out-of-sample boostrap model validation techniques when defect datasets are very small (i.e., EPV < 10).
    Preprint | DOI
  35. A Study of Redundant Metrics in Defect Prediction Datasets.
    Jirayus Jiarpakdee, Chakkrit Tantithamthavorn, Akinori Ihara, Kenichi Matsumoto, In Proceedings of the International Symposium on Software Reliability Engineering (ISSRE).
    Preprint
  36. Automated Parameter Optimization of Classification Techniques for Defect Prediction Models.
    Chakkrit Tantithamthavorn, Shane McIntosh, Ahmed E. Hassan, and Kenichi Matsumoto, In Proceedings of the International Conference on Software Engineering (ICSE). Acceptance Rate: 19% (101/530)
    (One-line Abstract): This paper suggested to explore various classification techniques and hyperparameter settings. We found that optimised random forest and optimised extreme gradient boosting trees often produce the most accurate defect prediction models.
    Preprint
  37. Towards a Better Understanding of the Impact of Experimental Components on Defect Prediction Modelling.
    Chakkrit Tantithamthavorn, In Proceedings of the International Conference on Software Engineering: Doctoral Symposium Track (ICSE-DS). Acceptance Rate: 22% (8/36) for paper presentation
    Preprint
  38. Comments on 'Researcher Bias: The Use of Machine Learning in Software Defect Prediction'.
    Chakkrit Tantithamthavorn, Shane McIntosh, Ahmed E. Hassan, Kenichi Matsumoto, IEEE Transactions on Software Engineering (TSE).
    Preprint | DOI
  39. The Impact of Mislabelling on the Performance and Interpretation of Defect Prediction Models.
    Chakkrit Tantithamthavorn, Shane McIntosh, Ahmed E. Hassan, Akinori Ihara, and Kenichi Matsumoto, In Proceedings of the International Conference on Software Engineering (ICSE). Acceptance Rate: 18.5% (89/455)
    Outstanding Paper Award for Young C&C Researchers by NEC C&C, Japan
    (One-line Abstract): This paper suggested not to be concerned about issue report misclassification.
    Preprint | DOI
  40. Who Should Review My Code? A File Location-Based Code-Reviewer Recommendation Approach for Modern Code Review.
    Patanamon Thongtanunam, Chakkrit Tantithamthavorn, Raula Gaikovina Kula, Norihiro Yoshida, Hajimu Iida, Kenichi Matsumoto, In Proceedings of the International Conference on Software Analysis, Evolution, and Reengineering (SANER). Acceptance Rate: 32% (46/144)
    Preprint | DOI
  41. Impact Analysis of Granularity Levels on Feature Location Technique.
    Chakkrit Tantithamthavorn, Akinori Ihara, Hideaki Hata, Kenichi Matsumoto, In Proceedings of the First Asia Pacific Requirements Engineering Symposium (APRES).
    Preprint
  42. Mining A Change History to Quickly Identify Bug Locations: A Case Study of the Eclipse Project.
    Chakkrit Tantithamthavorn, Rattamont Teekavanich, Akinori Ihara, Kenichi Matsumoto, In Proceedings of the International Symposium on Software Reliability Engineering (ISSRE).
    Preprint | DOI
  43. Using Co-Change Histories to Improve Bug Localization Performance.
    Chakkrit Tantithamthavorn, Akinori Ihara, Kenichi Matsumoto, In Proceedings of the International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD).
    Preprint | DOI
  44. Knowledge Discovery in Web Traffic Log: A Case Study of Facebook Usage in Kasetsart University.
    Chakkrit Tantithamthavorn and Arnon Rungsawang, In Proceedings of the International Joint Conference on Computer Science and Software Engineering (JCSSE).
    Preprint | DOI