Assessing Software Quality of Agile Student Projects by Data-mining Software Repositories

Abstract

Group student software projects are important in computer science education. Students are encouraged to self-organize and learn technical skills, preparing them for real life software development. However, the projects contribute to multiple learning objectives, making coaching students a time consuming task. Thus, it is important to have a suitable best practice development process. For providing better insights for the students, the resulting software has to be of value and meet quality requirements, including maintainability, as in real life software development. Using source code quality metrics and by data mining repository data like commit history, we analyze six student projects, measuring their quality and identifying contributing factors to success or failure of a student project. Based on the findings, we formulate recommendations to improve future projects for students and researchers alike.

Integrating GitLab metrics into coursework consultation sessions in a software engineering course

“…The activity metrics available from software development platforms, including VCSs and issue-tracking systems, have already been used for various purposes in an educational context such as describing student behaviours [1,2,3,4,5], correlating these behaviours with outcomes [6,7,8], predicting grades with supervised machine learning approaches [9,10,11,12,13,14], profiling student behaviours [15,16], conformance checking [17,18] and as a marking aid [19].…”