Learning analytics involves the collection and analysis of student and course data, including interactions with educational technology such as a learning management system (LMS), for the purposes of better understanding and optimizing student learning and learning environments. This research project will involve identifying, visualizing and analyzing LMS data from the University of Toronto to investigate how the data might effectively be used to identify student patterns of activity and their association with student success and how it might inform practices in learning design that can benefit all students. The particular question to be considered in this project will be determined based on available data and the interests and background of the research student. Possible questions that could be considered include: How do students interact with their instructor and each other in online discussion forums? How does student engagement with digital resources differ for courses presented in online and in-person delivery modes? Are there patterns of student activity that appear to be productive and patterns that do not? How can student LMS activity data be used as a proxy for student engagement and how might course design decisions affect the suitability of the data to effectively capture meaningful measures of engagement?

Learning analytics involves the collection and analysis of student and course data, including interactions with educational technology such as a learning management system (LMS), for the purposes of better understanding and optimizing student learning and learning environments. Most investigations of student engagement have focused on the course-level activity analysis. However, this project will investigate whether the analysis of engagement across courses and academic terms may inform program-level practices in learning design that can benefit all students.

The project will involve identifying, visualizing and analyzing LMS and administrative data from the University of Toronto to investigate how the data might effectively be used to identify student patterns of activity across courses and academic terms. Possible questions that could be considered include: Are there patterns of student activity across courses that appear to be productive and patterns that do not? How do these patterns vary with student program of study or prerequisite courses? Can LMS activity data be used as a proxy for student engagement across courses taken concurrently? What program-level aspects are related to changes in a student’s odds of dropping out of a course? The particular question will be determined based on the interests and background of the SUDS Scholar.