|Software Engineering Analytics research at University of Wollongong (SEA@UOW)|
The pervasiveness of software products in all areas of society has resulted in millions of software projects (e.g. over 17 million active projects on GitHub) and a massive amount of data about their development, operation and maintenance (e.g. the well-known Web browser, Mozilla Firefox project, currently has over 300 releases and 1.5 million issues reports since its initial release in 2002). This huge amount of software engineering data is continuously generated at a rapid rate in many forms such as user stories, use cases, requirements specifications, issue and bug reports, source code, test cases, execution logs, app reviews, user and develop mailing lists, discussion threads, and so on. Hidden in those Big Data are insights valuable to project managers, software engineers and other stakeholders about the quality of the development process and the software product, and the experience that software users receive.
Using cutting-edge machine learning and data mining techniques, our Software Engineering Analytics (SEA) research team aims to develop analytics technologies which specifically turn software engineering data into actionable insight. We believe that SEA will significantly improve the theory and practice of software engineering, enabling us to build better software and build software better, addressing both quality and productivity needs.
Below are some exemplar projects that we have done:
Using the same analytics data-driven approach, we can also build predictive models/recommendation systems for the following (but not limited to):
All the datasets used in our publications are made publicly available here. If you use our datasets, please cite our relevant paper in your publication.