Learning Analytics and Self-Regulated Learning

Learning analytics is the analysis and representation of student-produced data to aid administrators, teachers and students themselves in fostering learning success.

Tracking students' behavior in online learning environments and mirroring it back to them has been of significant interest to researchers in the learning analytics community (Clow, 2013; Ferguson, 2012; Greller & Drachsler, 2012; Siemens & Long, 2011). The researchers use data generated by students’ activity to construct visualizations which are presented to the students to influence and inform their decisions (Siemens, 2013). 

Drawing on relevant psychological theories, we propose design features that promote Self Regulate Learning (SRL) and construction of content knowledge. Specifically, we address ways to support planning and self-monitoring of learning strategies that, according to learning sciences research, benefit students. 

The learning analytics we design are based on the type of fine-grained learner data collected by nStudy, a browser extension developed in our lab with features that can help students be more effective learners. While learning, learners can perform different nStudy actions such as creating quotes, notes, and tags. nStudy collects time-stamped, fine-grained data when student clicks, marks, creates, reviews and edits content, and more (Winne et al., 2016). 

An example Learning Analytic developed in our lab

This learning analytic shows a visualization to a learner while studying 5 articles. 

The learner’s activities are mirrored in the diagram in relation to her goals. For example,  four out of the five articles were opened but only three were operated on by the learner.


LASI 2014 - Keynote Philip Winne

Voices from the Field - Philip Winne

LASI 2019 - Keynote Philip Winne