Engineering

Making Learning Visible in Software Engineering: A Learning Analytics Approach​

Software engineering education is inherently process-oriented. Students do not simply produce a final software product; they continuously interpret requirements, design solutions, write and review code, test, debug, collaborate, seek feedback, and revise their approaches. However, much of this learning remains invisible. Traditional assessment typically captures visible outputs - such as the final codebase, report, demonstration, or examination - while providing limited insight into how students reached those outcomes. ​

This project applies a learning analytics approach to examine software engineering processes through the lens of self-regulated learning (SRL). It involves designing and evaluating a Learning Analytics Dashboard (LAD) that transforms software development activity into indicators of learning and engagement, supporting student reflection and providing educators with evidence to guide learning support.​

Project Phases:

  1. Review the literature on self-regulated learning and identify relevant indicators that support monitoring, reflection, and behavioural adjustment.
  2. Co-design the LAD with potential users, such as software engineering students, and develop a functional prototype.
  3. Evaluate the LAD with a small group of users (e.g., a student focus group), focusing on usability, functionality, and usefulness.
Email
School

Computer Science and Engineering

Research Area

Educational data mining | User centred design | Process mining

Suitable for recognition of Work Integrated Learning (industrial training)?

No

Software/Tools:

  • GitLab and GitLab Analytics for software development activity data.
  • Node.js, TypeScript, and React/TSX for LAD development.
  • Figma or similar tools for interface prototyping and co-design.

Data:

  • GitLab activity data, such as commits, merge requests, issues, and code reviews.
  • De-identified or synthetic student software development activity data.
  • User feedback collected through co-design sessions, usability testing, and focus groups.
  1. A set of self-regulation indicators relevant to software engineering students.
  2. A functional LAD prototype providing self-regulation-oriented insights.
  3. A research report (15-20 pages) presenting the LAD’s design and evaluation findings on its usability, usefulness, and potential to support self-regulated learning.
Shaveen Singh

Shaveen Singh

View Profile
  1. Bistolfi, I., de Mooij, S., Sparou, C., Molenaar, I., & van der Graaf, J. (2026, July). Co-designing a Dashboard Promoting SRL for Secondary Education. In International Conference on Human-Computer Interaction (pp. 37-58). Cham: Springer Nature Switzerland. DOI: https://doi.org/10.1007/978-3-032-30781-1_3
  2. Aguilar, S. J., Karabenick, S. A., Teasley, S. D., & Baek, C. (2021). Associations between learning analytics dashboard exposure and motivation and self-regulated learning. Computers & Education, 162, 104085. DOI: 10.1016/j.compedu.2020.104085
  3. Matcha, W., Uzir, N. A. A., Gašević, D., & Pardo, A. (2019). A systematic review of empirical studies on learning analytics dashboards: A self-regulated learning perspective. IEEE transactions on learning technologies, 13(2), 226-245. DOI: 10.1109/TLT.2019.2916802