Time-driven modeling of student self-regulated learning in network-based tutors

ABSTRACT

This study applies a time-driven approach to model self-regulated learning (SRL) on the basis of elapsed time metrics in the context of open-ended learning environments (OELEs), specifically, network-based tutors. In doing so, we examine how students allocated attentional resources to distinct phases of SRL as a measure of depth of information processing. Student teachers (N=68) were assigned to two different versions of nBrowser: a static version where the network did not converge on the basis of student interactions and a dynamic version where the network was continually updated by the system. Students designed a lesson plan and completed pre- and post-test self-report measures of knowledge gains. In both the experimental conditions, the results show four distinct SRL profiles that are relatively consistent and can be detected on the basis of behavioral patterns logged by the system across behaviors, namely, planning, requesting hints, studying examples, and monitoring. Although students who allocated more attentional resources to studying examples performed more poorly, their efforts to engage in planning, requesting hints, and monitoring were found to predict knowledge gains and design skills. Furthermore, students assigned to the dynamic version of the system outperformed those assigned to the static version in pedagogical knowledge gains.

KEYWORDS:

• Self-regulated learning
• network-based tutors
• open-ended learning environments
• scaffolding
• time-driven modeling

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Eric G. Poitras

Eric G. Poitras is an Assistant Professor of Instructional Design and Educational Technology at the University of Utah. His research focuses on adaptive instructional systems and technologies, and their effects towards self-regulated learning processes.

Tenzin Doleck

Tenzin Doleck is an Assistant Professor and Canada Research Chair at Simon Fraser University.

Lingyun Huang

Lingyun Huang is a PhD candidate in the department of Educational and Counselling Psychology at McGill University, and a member of the ATLAS (Advanced Technologies for Learning in Authentic Settings) Lab. His research focuses on modeling the self-regulated learning (cognitive, metacognitive, and emotional) process in computer-based environments using educational data mining and multimode learning analytics approaches.

Laurel Dias

Laurel Dias is a doctoral student in the Learning Sciences program in the Educational Psychology department at the University of Utah. Her work focuses on teacher education, with a focus on digital learning environments and mathematics education. She is passionate about supporting teachers to use research-based practices in their instruction.

Susanne P. Lajoie

Susanne P. Lajoie is a Canadian Research Chair in Advanced Technologies for Learning in Authentic Settings in the Department of Educational and Counselling Psychology and an associate member of the Institute of Health Sciences Education at McGill University. She uses theories of learning and affect to design advanced technologies for learning in medicine. She is a Royal Society of Canada Fellow and a Fellow of the American Psychological Association and American Educational Research Association.