Learning Analytics and Survey Data Integration in Workload Research

Journal article
(Original article)

Publication Details

Author(s): Samoilova E, Keusch F, Wolbring T
Journal: Zeitschrift für Hochschulentwicklung
Publication year: 2017
Volume: 12
Journal issue: 2
Pages range: 65 - 78
ISSN: 0250-6467
Language: English


While Learning Analytics (LA) has a lot of potential, educators sometimes doubt whether it is worth to invest in the analysis of LA and whether its use yields additional insights. Drawing on data from a pilot study, we illustrate an application of LA for the evaluation of student workload in online or blended learning courses. Although measuring student workload is essential for optimizing learning, workload research is still under development. The study compares results provided by two data sources: viewing activity logs and a weekly evaluation survey. The results indicate that self-reported data provide higher estimates of workload than LA. Moreover, the two measures are only weakly correlated. The results should be replicated with a larger sample size, different sub-populations, and in different contexts.

FAU Authors / FAU Editors

Wolbring, Tobias Prof. Dr.
Lehrstuhl für Empirische Wirtschaftssoziologie

How to cite

Samoilova, E., Keusch, F., & Wolbring, T. (2017). Learning Analytics and Survey Data Integration in Workload Research. Zeitschrift für Hochschulentwicklung, 12(2), 65 - 78. https://dx.doi.org/10.3217/zfhe-12-01/04

Samoilova, Evgenia, Florian Keusch, and Tobias Wolbring. "Learning Analytics and Survey Data Integration in Workload Research." Zeitschrift für Hochschulentwicklung 12.2 (2017): 65 - 78.


Last updated on 2018-08-08 at 03:44