Applying Data-Mining Methods to Understand User Interactions Within Learning Management Systems: Approaches and Lessons Learned

• In Event: Roundtable Session 51
  In Roundtable Session: Student Perceptions and Interactions in Technology-Supported Learning

Abstract

This paper describes our processes for analyzing instructor and student usage data collected by a learning management system widely used in higher education, called Canvas. Our data were drawn from over 33,000 courses taught over three years at a mid-sized public Western U.S. university. Our processes were guided by a standard data mining methodology, called Knowledge Discovery from Data (KDD), consisting of three phases. In particular, we apply KDD methodology to analyze and model Canvas usage data and describe and document our EDM methods, as well as challenges and lessons learned along the way.

Authors

• Hongkyu Choi, Utah State University

• Won Joon Hong, Utah State University

• Nam Ju Kim, Utah State University

• Ji Eun Lee, Utah State University

• Kyumin Lee, Utah State University

• Mason Lefler, Utah State University

• John Louviere, Utah State University

• Mimi M. Recker, Utah State University

• Andrew Walker, Utah State University