Learning Analytics für Diversity-Inspired Adaptive Learning

LA DIVA is a CATALPA project.

Learners are individual, have different strengths, are in different stages of life, and therefore need different types of support, especially in digital distance learning. This is precisely where LA DIVA comes in and determines the potential of learning analytics.

Project goals and research questions

The goal of the project is to investigate the potential of Learning Analytics for supporting adaptive learning in distance education, with a particular focus on the diversity of the learners. This potential will be investigated on the basis of three central issues:

  1. Diversity-Inspired Adaptive Assessment: Possibilities for adapting the assessments and tasks offered in a concrete learning situation, with respect to three dimensions: selection of task types, parameterization/generation of tasks, and adaptive feedback and solution hints.
  2. Diversity-Inspired Adaptive Support for Collaborative Learning: Possibilities for supporting dynamic education and reconfiguration of learning groups as well as adaptive support for diverse learning groups on the basis of individual profiles, group profiles, and interaction data.
  3. Emergence of Student Profiles: Collection and analysis of student data as the basis for a long-term investigation into whether and how the diversity of the student body changes over time in relation to learning-relevant parameters.
  • Prof. Dr. Jörg Haake (FernUniversität) und Prof. Dr. Niels Pinkwart (HU, DFKI and Visiting Professor with CATALPA) - see also Cooperations.

  • 01 April 2020 through 31 December 2024

  • 2022


    • Burchart, M. (2022). Auf dem Weg zur skalierbaren Unterstützung des kollaborativen Schreibens in hochdiversen Fernlerngruppen. MedienPädagogik: Zeitschrift für Theorie und Praxis der Medienbildung, 48(Digitalisierung als Katalysator), 135–154.
    • Kasakowskij, R. (2022). Auswahl und Generierung von passenden Feedbacks auf Basis eines Feedback-Rating-System-Frameworks. MedienPädagogik: Zeitschrift für Theorie und Praxis der Medienbildung, 48(Digitalisierung als Katalysator), 155–169.
    • Kuzilek, J., Zdrahal, Z., Vaclavek, J., Fuglik, V., Skocilas, J., & Wolff, A. (2022). First-year engineering students’ strategies for taking exams. International Journal of Artificial Intelligence in Education, 1–26.


    • Diesner-Mayer, T., & Seidel, N. (2022). Supporting gender-neutral writing in German. Proceedings of the Conference on Mensch Und Computer, (im Druck).
    • Kasakowskij, R., Kasakowskij, T., & Seidel, N. (2022). Generation of Multiple True False Questions. In P. A. Henning, M. Striewe, & M. Wölfel (Eds.), DELFI 2021 – Die 20. Fachtagung Bildungstechnologien der Gesellschaft für Informatik e.V. (pp. 147–152). Gesellschaft für Informatik.
    • Schumacher, C., & Kuzilek, J. (2022). How do students perceive algorithmic grouping in higher education? Companion Proceedings of the LAK2022, 48.
    • Seidel, N. (2022). Modeling study duration considering course enrollments and student diversity. Proceedings of the 15th International Conference on Educational Data Mining (EDM 2022), 621–628.

    Data Sets




    • Schumacher, C., & Kuzilek, J. (2021a). Perfect match? Investigating students’ perceptions about algorithmic grouping in higher education. 2021 AECT International Convention.
    • Schumacher, C., & Kuzilek, J. (2021b, June). Student perspectives on automatic grouping in higher education. Presented at Junges Forum für Medien Und Hochschulentwicklung, Virtual Conference, 09-06-2021.
    • Schumacher, C., Reich-Stiebert, N., Kuzilek, J., Burchart, M., Raimann, J., Voltmer, J.-B., & Stürmer, S. (2021, April). Group perceptions vs. Group reality: Exploring the fit of self-report and log file data in the process of collaboration. Companion Proceedings of Conference on Learning Analytics and Knowledge 2021, Virtual Conference, 15-04-2021.
    • Seidel, N. (2021). Designing Systems for Mobile Collaboration. 26th European Conference on Pattern Languages of Programs, Article 22, 13 pages.
    • Weiher, B., Seidel, N., Burchart, M., & Veiel, D. (2021). Indicators of group learning in collaborative software development teams. In Andreas Lingnau (Ed.), Proceedings of DELFI workshops 2021 (pp. 164–175). Gesellschaft für Informatik.