Incorporating Time in Dispositional Learning Analytics Models

Learning analytics needs to pay more attention to the temporal aspect of learning processes, especially in self-regulated learning 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 are well presented as events, but does paying tribute to temporal aspects necessarily imply that event-based models are to replace variable-based models and that analytic discovery methods 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. On the contrary, temporal aspects are well integrated into variable-based models that apply statistical methods by carefully choosing time windows and granularity levels, with the additional advantages that we can easily complement such models with other data, like disposition data representing student aptitudes, and that those models can be grounded on educational theories of learning processes. Our conjecture is illustrated by an application of dispositional learning analytics, describing authentic learning processes over an 8-week full course of 2628 students.