Modeling Student Teachers' Self-Regulated Learning Profiles With Network-Based Tutors

• In Event: Learner Analytics and Design Thinking: Using Technology to Assess and Support Learners

Abstract

Intelligent tutoring systems are assumed to be adaptive in terms of instructions to satisfy individual learners’ special needs and interests. This study made the use of nBrowser – an intelligent web browser – to model student teachers’ self-regulated learning behaviors by mining the log trace data of user interactions. The findings indicate that two distinct profiles of self-regulated learning: (1) information seeking and acquisition and (2) task solution construction. These profiles are most differentiated by learners’ time elapsed during the learning session, the count of lesson plan edits, and the time spent viewing online resource across conditions. Particularly, time spent in the learning session is the most predictive.

Authors

• Eric G. Poitras, University of Utah

• Tenzin Doleck, McGill University

• Lingyun Huang, McGill University

• Shan Li, McGill University

• Susanne P. Lajoie, McGill University