Copy the page URI to the clipboard
Tempelaar, D; Rienties, Bart; Giesbers, G and Nguyen, Quan
(2023).
DOI: https://doi.org/10.18608/jla.2023.7841
Abstract
Learning analytics needs to pay more attention to the temporal aspect of learning processes, especially in self-regulated learning (SRL) research. In doing so, learning analytics models should incorporate both the duration and frequency of learning activities, the passage of time, and the temporal order of learning activities. However, where this exhortation is widely supported, there is less agreement on its consequences. Temporal aspects of learning processes could be presented as events, but does paying tribute to temporal aspects necessarily imply that event-based models are to replace variable-based models, and whether analytic discovery methods could or even should substitute traditional statistical methods? Our contribution will reason that we do not require such a paradigm shift to give temporal aspects the position it deserves. First, we argue that temporal aspects can be well integrated into variable-based models that apply statistical methods by carefully choosing appropriate time windows and granularity levels. Our second argument is that in addressing temporality in learning analytic models that describe authentic learning settings, heterogeneity is of crucial importance in both variable and event-based models. Variable-based person-centered modeling where a heterogeneous sample is split into homogeneous subsamples is suggested as a solution. Our conjecture is illustrated by an application of dispositional learning analytics, describing authentic learning processes over an eight-week full module of 2,360 students.