REBRO, Dominik Arne, Bruno ROSSI and Stanislav CHREN. Source Code Metrics for Software Defects Prediction. Online. In The 38th ACM/SIGAPP Symposium on Applied Computing (SAC '23). Not specified: Association for Computing Machinery (ACM), 2023, p. 1469-1472. ISBN 978-1-4503-9517-5. Available from: https://dx.doi.org/10.1145/3555776.3577809.
Other formats:   BibTeX LaTeX RIS
Basic information
Original name Source Code Metrics for Software Defects Prediction
Authors REBRO, Dominik Arne (703 Slovakia, belonging to the institution), Bruno ROSSI (380 Italy, guarantor, belonging to the institution) and Stanislav CHREN (703 Slovakia, belonging to the institution).
Edition Not specified, The 38th ACM/SIGAPP Symposium on Applied Computing (SAC '23), p. 1469-1472, 4 pp. 2023.
Publisher Association for Computing Machinery (ACM)
Other information
Original language English
Type of outcome Proceedings paper
Field of Study 10200 1.2 Computer and information sciences
Confidentiality degree is not subject to a state or trade secret
Publication form electronic version available online
RIV identification code RIV/00216224:14330/23:00130144
Organization unit Faculty of Informatics
ISBN 978-1-4503-9517-5
Doi http://dx.doi.org/10.1145/3555776.3577809
UT WoS 001124308100207
Keywords in English Software Defect ; Software Metrics; Mining Software Repositories; Software Quality
Tags firank_A
Tags International impact, Reviewed
Changed by Changed by: RNDr. Pavel Šmerk, Ph.D., učo 3880. Changed: 7/4/2024 22:36.
Abstract
In current research, there are contrasting results about the applicability of software source code metrics as features for defect prediction models. The goal of the paper is to evaluate the adoption of software metrics in models for software defect prediction, identifying the impact of individual source code metrics. With an empirical study on 275 release versions of 39 Java projects mined from GitHub, we compute 12 software metrics and collect software defect information. We train and compare three defect classification models. The results across all projects indicate that Decision Tree (DT) and Random Forest (RF) classifiers show the best results. Among the highest-performing individual metrics are NOC, NPA, DIT, and LCOM5. While other metrics, such as CBO, do not bring significant improvements to the models.
Links
CZ.02.1.01/0.0/0.0/16_019/0000822, interní kód MU
(CEP code: EF16_019/0000822)		Name: Centrum excelence pro kyberkriminalitu, kyberbezpečnost a ochranu kritických informačních infrastruktur (Acronym: C4e)
Investor: Ministry of Education, Youth and Sports of the CR, CyberSecurity, CyberCrime and Critical Information Infrastructures Center of Excellence, Priority axis 1: Strengthening capacities for high-quality research
EF16_019/0000822, research and development projectName: Centrum excelence pro kyberkriminalitu, kyberbezpečnost a ochranu kritických informačních infrastruktur
PrintDisplayed: 6/10/2024 21:15