The Effect of Granularity Level on Software Defect Prediction

Calikli, G. , Tosun, A., Bener, A. and Celik, M. (2009) The Effect of Granularity Level on Software Defect Prediction. In: 2009 24th International Symposium on Computer and Information Sciences, Guzelyurt, Cyprus, 14-16 Sep 2009, pp. 531-536. ISBN 9781424450213 (doi: 10.1109/ISCIS.2009.5291866)

Full text not currently available from Enlighten.


Application of defect predictors in software development helps the managers to allocate their resources such as time and effort more efficiently and cost effectively to test certain sections of the code. In this research, we have used naive Bayes classifier (NBC) to construct our defect prediction framework. Our proposed framework uses the hierarchical structure information about the source code of the software product, to perform defect prediction at a functional method level and source file level. We have applied our model on SoftLAB and Eclipse datasets. We have measured the performance of our proposed model and applied cost benefit analysis. Our results reveal that source file level defect prediction improves the verification effort, while decreasing the defect prediction performance in all datasets.

Item Type:Conference Proceedings
Glasgow Author(s) Enlighten ID:Calikli, Dr Handan Gul
Authors: Calikli, G., Tosun, A., Bener, A., and Celik, M.
College/School:College of Science and Engineering > School of Computing Science

University Staff: Request a correction | Enlighten Editors: Update this record