Code review analysis of software system using machine learning techniques

Code review is systematic examination of a software system's source code. It is intended to find mistakes overlooked in the initial development phase, improving the overall quality of software and reducing the risk of bugs among other benefits. Reviews are done in various forms such as pair programming, informal walk-through, and formal inspections. Code review has been found to accelerate and streamline the process of software development like very few other practices in software development can. In this paper we propose a machine learning approach for the code reviews in a software system. This would help in faster and a cleaner reviews of the checked in code. The proposed approach is evaluated for feasibility on an open source system eclipse. [1], [2], [3]

[1]  Andreas Zeller,et al.  When do changes induce fixes? , 2005, ACM SIGSOFT Softw. Eng. Notes.

[2]  Alberto Bacchelli,et al.  Expectations, outcomes, and challenges of modern code review , 2013, 2013 35th International Conference on Software Engineering (ICSE).

[3]  Mark C. Paulk,et al.  The Impact of Design and Code Reviews on Software Quality: An Empirical Study Based on PSP Data , 2009, IEEE Transactions on Software Engineering.

[4]  Adam Krzyżak,et al.  Methods of combining multiple classifiers and their applications to handwriting recognition , 1992, IEEE Trans. Syst. Man Cybern..

[5]  Andreas Zeller,et al.  Classifying code changes and predicting defects using changegenealogies , 2013 .

[6]  Yi Zhang,et al.  Classifying Software Changes: Clean or Buggy? , 2008, IEEE Transactions on Software Engineering.

[7]  Ke Chen,et al.  Methods of Combining Multiple Classifiers with Different Features and Their Applications to Text-Independent Speaker Identification , 1997, Int. J. Pattern Recognit. Artif. Intell..

[8]  Andreas Zeller,et al.  Change Bursts as Defect Predictors , 2010, 2010 IEEE 21st International Symposium on Software Reliability Engineering.

[9]  Jesús M. González-Barahona,et al.  The MetricsGrimoire Database Collection , 2015, 2015 IEEE/ACM 12th Working Conference on Mining Software Repositories.

[10]  Andy Zaidman,et al.  Modern code reviews in open-source projects: which problems do they fix? , 2014, MSR 2014.

[11]  Mattias Liljeson,et al.  Software defect prediction using machine learning on test and source code metrics , 2014 .

[12]  Premkumar T. Devanbu,et al.  BugCache for inspections: hit or miss? , 2011, ESEC/FSE '11.