Change-Prone Java Method Prediction by Focusing on Individual Differences in Comment Density
Summary :
This paper focuses on differences in comment densities among individual programmers, and proposes to adjust the conventional code complexity metric (the cyclomatic complexity) by using the abnormality of the comment density. An empirical study with nine popular open source Java products (including 103,246 methods) shows that the proposed metric performs better than the conventional one in predicting change-prone methods; the proposed metric improves the area under the ROC curve (AUC) by about 3.4% on average.
- Publication
- IEICE TRANSACTIONS on Information Vol.E100-D No.5 pp.1128-1131
- Publication Date
- 2017/05/01
- Publicized
- 2017/02/15
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2016EDL8224
- Type of Manuscript
- LETTER
- Category
- Software Engineering
Authors
Aji ERY BURHANDENNY
Ehime University,Mulawarman University
Hirohisa AMAN
Ehime University
Minoru KAWAHARA
Ehime University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Aji ERY BURHANDENNY, Hirohisa AMAN, Minoru KAWAHARA, "Change-Prone Java Method Prediction by Focusing on Individual Differences in Comment Density" in IEICE TRANSACTIONS on Information,
vol. E100-D, no. 5, pp. 1128-1131, May 2017, doi: 10.1587/transinf.2016EDL8224.
Abstract: This paper focuses on differences in comment densities among individual programmers, and proposes to adjust the conventional code complexity metric (the cyclomatic complexity) by using the abnormality of the comment density. An empirical study with nine popular open source Java products (including 103,246 methods) shows that the proposed metric performs better than the conventional one in predicting change-prone methods; the proposed metric improves the area under the ROC curve (AUC) by about 3.4% on average.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2016EDL8224/_p
Copy
@ARTICLE{e100-d_5_1128,
author={Aji ERY BURHANDENNY, Hirohisa AMAN, Minoru KAWAHARA, },
journal={IEICE TRANSACTIONS on Information},
title={Change-Prone Java Method Prediction by Focusing on Individual Differences in Comment Density},
year={2017},
volume={E100-D},
number={5},
pages={1128-1131},
abstract={This paper focuses on differences in comment densities among individual programmers, and proposes to adjust the conventional code complexity metric (the cyclomatic complexity) by using the abnormality of the comment density. An empirical study with nine popular open source Java products (including 103,246 methods) shows that the proposed metric performs better than the conventional one in predicting change-prone methods; the proposed metric improves the area under the ROC curve (AUC) by about 3.4% on average.},
keywords={},
doi={10.1587/transinf.2016EDL8224},
ISSN={1745-1361},
month={May},}
Copy
TY - JOUR
TI - Change-Prone Java Method Prediction by Focusing on Individual Differences in Comment Density
T2 - IEICE TRANSACTIONS on Information
SP - 1128
EP - 1131
AU - Aji ERY BURHANDENNY
AU - Hirohisa AMAN
AU - Minoru KAWAHARA
PY - 2017
DO - 10.1587/transinf.2016EDL8224
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E100-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2017
AB - This paper focuses on differences in comment densities among individual programmers, and proposes to adjust the conventional code complexity metric (the cyclomatic complexity) by using the abnormality of the comment density. An empirical study with nine popular open source Java products (including 103,246 methods) shows that the proposed metric performs better than the conventional one in predicting change-prone methods; the proposed metric improves the area under the ROC curve (AUC) by about 3.4% on average.
ER -
English
