A Methodology for Using GitLab for Software Engineering Learning Analytics
This work addresses the need for better training tools in software engineering education, but it is incremental as it applies existing analytics methods to a new educational context.
The paper tackled the problem of analyzing student software engineering learning patterns using GitLab data to improve course content, focusing on building a Learning Analytics pipeline that addresses data anonymization for privacy compliance.
To bridge the digital skills gap, we need to train more people in Software Engineering techniques. This paper reports on a project exploring the way students solve tasks using collaborative development platforms and version control systems, such as GitLab, to find patterns and evaluation metrics that can be used to improve the course content and reflect on the most common issues the students are facing. In this paper, we explore Learning Analytics approaches that can be used with GitLab and similar tools, and discuss the challenges raised when applying those approaches in Software Engineering Education, with the objective of building a pipeline that supports the full Learning Analytics cycle, from data extraction to data analysis. We focus in particular on the data anonymisation step of the proposed pipeline to explore the available alternatives to satisfy the data protection requirements when handling personal information in academic environments for research purposes.