Logo des Repositoriums

Auflistung nach Autor:in "Baucks, Frederik"

1 - 3 von 3
  • Konferenzbeitrag
    Ein Dashboard für die Studienberatung: Technische Infrastruktur und Studienverlaufsplanung im Projekt KI:edu.nrw
    (Workshops der 21. Fachtagung Bildungstechnologien (DELFI), 2023) Baucks, Frederik; Leschke, Jonas; Metzger, Christian; Wiskott, Laurenz
    In diesem Beitrag präsentieren wir die Entwicklung und ein erster Prototyp für ein Learning Analytics-Dashboard zur Studienverlaufsplanung in der Studienberatung. Das Dashboard wird im Rahmen des interdisziplinären Projekts KI:edu.nrw entwickelt, mit dem Ziel, die Studienberatung zu verbessern und einen individuellen Studienverlauf zu fördern. Unser Beitrag konzentriert sich auf die Vorstellung der technischen Infrastruktur sowie deren Anwendung in dem speziellen Dashboard.
  • Konferenzbeitrag
    Mitigating Biases using an Additive Grade Point Model: Towards Trustworthy Curriculum Analytics Measures
    (21. Fachtagung Bildungstechnologien (DELFI), 2023) Baucks, Frederik; Wiskott, Laurenz
    Curriculum Analytics (CA) tries to improve degree program quality and learning experience by studying curriculum structure and student data. In particular, descriptive data measures (e.g., correlation-based curriculum graphs) are essential to monitor whether the learning process proceeds as intended. Therefore, identifying confounders and resulting biases and mitigating them should be critical to ensure reliable and fair results. Still, CA approaches often use raw student data without considering the influence of possible confounders such as student performance, course difficulty, workload, and time, which can lead to biased results. In this paper, we use an additive grade model to estimate these confounders and verify the validity and reliability of the estimates. Further, we mitigate the estimated confounders and investigate their impact on the CA measures course-to-course correlation and order benefit. Using data from 574 Computer Science Bachelor students, we show that these measures are significantly confounded and mislead to biased interpretations.
  • Textdokument
    Workshop Learning Analytics: Study Path and Curriculum Analytics
    (Proceedings of DELFI Workshops 2024, 2024) Cohausz, Lea; Baucks, Frederik; Seidel, Niels
    Learning analytics holds substantial potential for understanding learners and educational environments. Yet, the study of curriculum analytics and learner pathways is still a developing field, often limited to isolated studies of specific courses and programs. Researchers in Germany and the European Union face legal restrictions (e.g., GDPR) and data quality issues, which limit access to comprehensive data. These limitations hinder understanding factors influencing student success and study duration, which affects improving curricula. The workshop features expert presenters who offer diverse perspectives on these topics, sharing their insights, models, and tools to support stakeholders, including students, teachers, and university administrations. Subsequent discussions among the interdisciplinary participants from the German and Austrian areas highlight the current situation and pave the way for future curriculum analytics.