Další formáty:
BibTeX
LaTeX
RIS
@inproceedings{1408417,
author = {Singha Roy, Nivir Kanti and Rossi, Bruno},
address = {Not specified},
booktitle = {43rd Euromicro Conference on Software Engineering and Advanced Applications (SEAA) 2017},
doi = {http://dx.doi.org/10.1109/SEAA.2017.71},
keywords = {cost-sensitive strategies; data imbalance; software bug severity classification; software bug triaging process; support vector machine; SVM classifier},
howpublished = {elektronická verze "online"},
language = {eng},
location = {Not specified},
isbn = {978-1-5386-2140-0},
pages = {426-429},
publisher = {IEEE},
title = {Cost-Sensitive Strategies for Data Imbalance in Bug Severity Classification: Experimental Results},
url = {http://ieeexplore.ieee.org/document/8051382/},
year = {2017}
}
TY - JOUR
ID - 1408417
AU - Singha Roy, Nivir Kanti - Rossi, Bruno
PY - 2017
TI - Cost-Sensitive Strategies for Data Imbalance in Bug Severity Classification: Experimental Results
PB - IEEE
CY - Not specified
SN - 9781538621400
KW - cost-sensitive strategies
KW - data imbalance
KW - software bug severity classification
KW - software bug triaging process
KW - support vector machine
KW - SVM classifier
UR - http://ieeexplore.ieee.org/document/8051382/
N2 - 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.
ER -
SINGHA ROY, Nivir Kanti a Bruno ROSSI. Cost-Sensitive Strategies for Data Imbalance in Bug Severity Classification: Experimental Results. Online. In \textit{43rd Euromicro Conference on Software Engineering and Advanced Applications (SEAA) 2017}. Not specified: IEEE, 2017, s.~426-429. ISBN~978-1-5386-2140-0. Dostupné z: https://dx.doi.org/10.1109/SEAA.2017.71.
|
