Studying the effectiveness of deep active learning in software defect prediction

Abstract

Accurate prediction of defective software modules is of great importance for prioritizing quality assurance efforts, reasonably allocating testing resources, reducing costs and improving software quality. Several studies have used machine learning to predict software defects. However, complex structures and imbalanced class distributions in software defect data make learning an effective defect prediction model challenging. In this article, two deep learning-based defect prediction models using static code metrics are proposed. In order to enhance the learning process and improve the performance of the proposed models, pool-based active learning is employed. In this regard, the possibility of using active learning to mitigate the need for a large amount of labeled data in the process of building deep learning models is investigated. To deal with imbalanced distribution of software modules between defective and non-defective classes, Near-Miss under-sampling and KNN, with different number of neighbors, are used. The reason for choosing them is their good performance in binary classification problems. Experiments are performed on two well-known, publicly available datasets, GitHub Bug Dataset and public Unified Bug Dataset for java projects. The evaluation results reveal the effectiveness of our proposed models in comparison to the traditional machine learning algorithms. In the conducted investigations on the Unified Bug Dataset, at the file level, the value of F-measure and AUC criteria have improved by 13 and 11 percent, respectively and at the class level, the values have improved by 14 and 11 percent, respectively.

KEYWORDS:

• Bug prediction
• code metrics
• active learning
• deep learning

Disclosure statement

No potential conflict of interest was reported by the author(s).

Notes

1 https://github.com/sed-inf-u-szeged/OpenStaticAnalyzer

2 http://www.inf.u-szeged.hu/~ferenc/papers/UnifiedBugDataSet

Additional information

Notes on contributors

Farid Feyzi

Farid Feyzi received his M.S. degree in Software Engineering from the Sharif University of Technology in 2012, and his Ph.D. in Software Engineering from the Iran University of Science and Technology in 2018. He is an assistant professor of Software Engineering at the University of Guilan. His research focus is on developing statistical algorithms to improve software quality with an emphasis on statistical fault localization and automated test data generation.

Arman Daneshdoost

Arman Daneshdoost recieved his M.S. degree in Software Engineering from University of Guilan in 2020. His research focus is on designing, developing and fine tunning deep learning models and transformers to improve the performance of automated industrial and service based systems and applications.