As open source software systems are becoming bigger and more complex, the bug detection task and fixing it to improve the performance of the software is also getting complex, time taking, and inefficient. Users are permitted by the developers to report bugs that are found by them using a bug tracking system such as Bugzilla to improve the quality and efficiency of the software. In Bugzilla, users identify clearly the details of the bug, such as the description, the component, the version, the product, and the severity. Depending on this information, the priority levels to the reported bugs are assigned by the developers according to their severity. In this research, the model is proposed that is a customized version of a classification technique called “Customized Cascading Randomized Weighted Majority Voting”. This technique will include an ensemble of two base classifiers: Naïve Bayes classifier and Random Forest classifier with different proposed weights in case of textual datasets.

Eclipse, Priority Prediction, Severity Prediction, Machine Learning, Textual Analysis, Bugzilla, Jupyter Notebook

[1] S. Kim, E. J. Whitehead, “How long did it take to fix bugs?”, MSR `06 Proceedings of the 2006 international workshop on Mining software repositories, Shanghai, China, pp.173-174, 2006.
[2] S. Gujral, G. Sharma, “Classifying Bug Severity Using Dictionary Based Approach”, International Conference on Futuristic trend in Computational Analysis and Knowledge (ABLAZE 2015), Noida, India, pp.632-639, 2015.
[3] D. Cubranic, G. C. Murphy, “Automatic bug triage using text categorization”, 16th International Conference on Software Engineering, Italy, pp.92-97, 2004.
[4] V. Challagulla, F. Bastani, I.-L. Yen, R. Paul, “Empirical Assessment of Machine Learning Based Software Defect Prediction Techniques.”, 10th IEEE International Workshop on Object-Oriented Real-Time Dependable Systems., Arizona, USA, pp.263-270, 2005.
[5] S N Ahsan , J. Ferzund , F. Wotawa, “Automatic Software Bug Triage System (BTS) Based on Latent Semantic Indexing and Support Vector Machine”, Proceedings of the 2009 Fourth International Conference on Software Engineering Advances, Portugal, pp.216-221, 2009.
[6] Lamkanfi, S. Demeyer, E. Giger, B. Goethals, “Predicting the severity of a reported bug.”, 7th IEEE Working Conference Mining Software Repositories (MSR), South Africa, pp.1-10, 2010.
[7] Lamkanfi, Ahmed, et al. "Comparing mining algorithms for predicting the severity of a reported bug", 15th European Conference on Software Maintenance and Reengineering (CSMR), Germany, pp.249-258, 2011.
[8] T. Menzies, A. Marcus, “Automated severity assessment of software defect reports,” in IEEE International Conference on Software Maintenance, China, pp.346–355, 2008.
[9] M.N. Pushpalatha, M. Mrunalini, “Predicting the Severity of Bug Reports using Classification Algorithms”, 2016 International Conference on Circuits, Controls, Communications and Computing (I4C), Bangalore, India, pp.520-525, 2016.
[10] S. Sharma, P. Rana, “Implementing Bug Severity Prediction through Information Mining using KNN Classifier”, International Journal of Science Technology & Engineering, Vol. 2, Issue 4, pp.333 – 340, 2015
[11] G. Yang, T. Zhang, “Towards Semi-automatic Bug Triage and Severity Prediction Based on Topic Model and Multi-Feature of Bug Reports”, 2014 IEEE 38th Annual International Computers, Software and Applications Conference, Sweden, pp.97-106, 2014.
[12] Herraiz, D. German, J. Gonzalez-Barahona, G. Robles, “Towards a Simplification of the Bug Report Form in Eclipse,” in 5th International Working Conference on Mining Software Repositories, Germany, pp.145-148, May 2008.
[13] J. Anvik, L. Hiew, and G. Murphy, “Who should fix this bug?” in Proc 28th International Conference on Software Engineering. ACM, China, pp.361–370, 2006.