Predicting the severity of bug reports using classification algorithms

Bug triaging is the process of prioritizing the bug reports based on the severity and is driven by the business needs and available resources. Majority times, only few of the reported bugs are selected to be fixed. The selected bugs are prioritized (ordered) based on their severity (e.g. the bug inhibits an important feature of the product, the bug affects a large number of users) and then fixed according to their priority. If the severity is assigned incorrectly then time and resources may be wasted to fix that bug. Hence there is a need for new techniques to avoid this misuse of resources. In this paper, bagging ensemble method is used for predicting the severity of bug reports. Also, bagging ensemble method is compared with C4.5 classifier. The results have shown that bagging ensemble method gives better accuracy compared to C4.5 general classifier on the given dataset.

[1]  Franz Wotawa,et al.  Automatic Software Bug Triage System (BTS) Based on Latent Semantic Indexing and Support Vector Machine , 2009, 2009 Fourth International Conference on Software Engineering Advances.

[2]  Gail C. Murphy,et al.  Who should fix this bug? , 2006, ICSE.

[3]  K. K. Chaturvedi,et al.  An Empirical Comparison of Machine Learning Techniques in Predicting the Bug Severity of Open and Closed Source Projects , 2012, Int. J. Open Source Softw. Process..

[4]  Gail C. Murphy,et al.  Reducing the effort of bug report triage: Recommenders for development-oriented decisions , 2011, TSEM.

[5]  K. K. Chaturvedi,et al.  Determining Bug severity using machine learning techniques , 2012, 2012 CSI Sixth International Conference on Software Engineering (CONSEG).

[6]  Serge Demeyer,et al.  Comparing Mining Algorithms for Predicting the Severity of a Reported Bug , 2011, 2011 15th European Conference on Software Maintenance and Reengineering.

[7]  R. K. Singh,et al.  Multiattribute Based Machine Learning Models for Severity Prediction in Cross Project Context , 2014, ICCSA.

[8]  Bart Goethals,et al.  Predicting the severity of a reported bug , 2010, 2010 7th IEEE Working Conference on Mining Software Repositories (MSR 2010).

[9]  Jun Yan,et al.  Automatic Bug Triage using Semi-Supervised Text Classification , 2017, SEKE.

[10]  Kenneth Magel,et al.  Efficient Bug Triaging Using Text Mining , 2013, J. Softw..

[11]  Tim Menzies,et al.  Automated severity assessment of software defect reports , 2008, 2008 IEEE International Conference on Software Maintenance.

[12]  David Lo,et al.  Information Retrieval Based Nearest Neighbor Classification for Fine-Grained Bug Severity Prediction , 2012, 2012 19th Working Conference on Reverse Engineering.

[13]  David Broman,et al.  Automated bug assignment: Ensemble-based machine learning in large scale industrial contexts , 2016, Empirical Software Engineering.