The Impact of the bug number on Effort-Aware Defect Prediction: An Empirical Study.
Abstract
should be disclosed when publishing software defect datasets, in order to construct more accurate EADP models. Previous research have utilized public software defect datasets such as NASA, RELINK, and SOFTLAB, which only contain class label information. Almost all Effort-Aware Defect Prediction (EADP) studies are carried out around these datasets. However, EADP studies typically relying on bug density (i.e., the ratio between bug numbers and the lines of code) for ranking software modules. In order to investigate the impact of neglecting bug number information in software defect datasets on the performance of EADP models, we examine the performance degradation of the best-performing learning to rank methods when class labels are utilized instead of bug numbers. The experimental results show that neglecting bug number information in building EADP models results in an increase in the detected bugs. However, it also leads to a significant increase in the initial false alarms, ranging from 45.5% to 90.9% of the datasets, and an significant increase in the modules that need to be inspected, ranging from 5.2% to 70.4%. Therefore, we recommend not only the class labels but also the bug number information CCS CONCEPTS • Software and its engineering → Software defect analysis; • Computing methodologies → Cross-validation; Machine learning approaches. KEYWORDS Software Defect Prediction, Effort-Aware, Bug Number, Learning to Rank ACM Reference Format: Peixin Yang, Lin Zhu, Wenhua Hu, Jacky Wai Keung, Liping Lu, and Jianwen Xiang. 2023. The Impact of the bug number on Effort-Aware Defect Prediction: An Empirical Study . In 14th Asia-Pacific Symposium on Internetware (Internetware 2023), August 04-06, 2023, Hangzhou, China. ACM, New York, NY, USA, 12 pages. https://doi.org/10.1145/3609437.3609458 1 ∗ Corresponding author INTRODUCTION Software bugs have an obvious influence on the software quality and even the economy of software. Early detection of buggy modules in software development is an urgent problem that needs to be solved. Software Defect Prediction (SDP) is one of the feasible methods, which employs machine learning techniques to predict whether there exist