Process Mining Measures Students' Sequential Self-Regulated Learning Processes When Completing Assignments in Online Learning Environments

• In Event: Statistical Methods for Assessing Self-Regulated Learning in Context

Abstract

Measuring the contingent nature of self-regulated learning within behavioral sequences is necessary for understanding how students learn in autonomous online environments. Dynamic SRL processes can be measured with log data generated from online learning behaviors and modelled with parallel analyses that capture dynamic processes and individual behaviors between learners. This study used process mining and frequency analysis to identify sequential SRL processes and understand how processes and individual behaviors differ across learners in online environments. Findings reveal that help-seeking behaviors become more disorganized as students become more dysregulated in their learning, in which low performers repeatedly ask for help without attempting questions. The complimentary role of parallel analyses better capture the dynamic and iterative process involved in self-regulated learning.

Authors

• Chenyu Hou, National Institute of Education - Nanyang Technological University
  Presenting Author

• Shelbi Laura Kuhlmann, University of North Carolina - Chapel Hill
  Presenting Author

• Matthew L. Bernacki, University of North Carolina - Chapel Hill
  Non-Presenting Author

• Jeff A. Greene, University of North Carolina - Chapel Hill
  Non-Presenting Author

• Robert D Plumley, University of North Carolina - Chapel Hill
  Non-Presenting Author

• Kelly Hogan, University of North Carolina - Chapel Hill
  Non-Presenting Author

• Kathleen M. Gates, University of North Carolina - Chapel Hill
  Non-Presenting Author

• A. T. Panter, University of North Carolina - Chapel Hill
  Non-Presenting Author