Automated Impact Analyses to Support Code Review Practices
Large software systems are updated incrementally to add new features or fix bugs. It is a common practice in the software industry to have each incremental change reviewed by a peer to detect software quality issues and transfer knowledge among team members. While peer review boasts technical and non-technical benefits, it is still primarily based on low-level textual differencing, which place the prior and updated versions of the software source code next to one another. In this project, we will develop a tool to display high-level impact data (e.g., the areas of the released software system that are impacted by the change) by data mining archives of historical change data. We suspect that these improved tools will help Dell EMC (our partner organization) to improve the feedback being generated by their peer reviewing process and avoid costly software quality issues.