Advancing Temporal Methods for the Analysis of Self-Regulated Learning

Current methods for studying how students regulate their own learning fail to adequately capture how these behaviours change over time during a task. This thesis introduces new analytical methods that provide detailed, moment-by-moment insights into how learners self-regulate. These methods can automatically identify individual learning tactics as they unfold, enabling personalised understanding of each learner's approach. This work advances our ability to both measure and support self-regulated learning in educational settings.