SINGHA ROY, Nivir Kanti and Bruno ROSSI. Cost-Sensitive Strategies for Data Imbalance in Bug Severity Classification: Experimental Results. Online. In 43rd Euromicro Conference on Software Engineering and Advanced Applications (SEAA) 2017. Not specified: IEEE, 2017, p. 426-429. ISBN 978-1-5386-2140-0. Available from: https://dx.doi.org/10.1109/SEAA.2017.71.
Other formats:   BibTeX LaTeX RIS
Basic information
Original name Cost-Sensitive Strategies for Data Imbalance in Bug Severity Classification: Experimental Results
Authors SINGHA ROY, Nivir Kanti (50 Bangladesh) and Bruno ROSSI (380 Italy, guarantor, belonging to the institution).
Edition Not specified, 43rd Euromicro Conference on Software Engineering and Advanced Applications (SEAA) 2017, p. 426-429, 4 pp. 2017.
Publisher IEEE
Other information
Original language English
Type of outcome Proceedings paper
Field of Study 10201 Computer sciences, information science, bioinformatics
Country of publisher United States of America
Confidentiality degree is not subject to a state or trade secret
Publication form electronic version available online
WWW URL
RIV identification code RIV/00216224:14330/17:00100027
Organization unit Faculty of Informatics
ISBN 978-1-5386-2140-0
Doi http://dx.doi.org/10.1109/SEAA.2017.71
UT WoS 000426074600063
Keywords in English cost-sensitive strategies; data imbalance; software bug severity classification; software bug triaging process; support vector machine; SVM classifier
Tags core_B, firank_B
Tags International impact, Reviewed
Changed by Changed by: Bruno Rossi, PhD, učo 232464. Changed: 20/11/2019 10:02.
Abstract
Context: Software Bug Severity Classification can help to improve the software bug triaging process. However, severity levels present a high-level of data imbalance that needs to be taken into account. Aim: We investigate cost-sensitive strategies in multi-class bug severity classification to counteract data imbalance. Method: We transform datasets from three severity classification papers to a common format, totaling 17 projects. We test different cost sensitive strategies to penalize majority classes. We adopt a Support Vector Machine (SVM) classifier that we also compare to a baseline "majority class" classifier. Results: A model weighting classes based on the inverse of instance frequencies yields a statistically significant improvement (low effect size) over the standard unweighted SVM model in the assembled dataset. Conclusions: Data imbalance should be taken more into consideration in future severity classification research papers.
PrintDisplayed: 3/10/2024 05:23