Using Temporal Analytics to Detect Inconsistencies Between Learning Design and Student Engagement
Learning analytics has the potential to make the temporal dimensions of learning processes more visible using fine-grained proxies of how and when students engage with online learning activities. In this talk, I will demonstrate the extent to which students actually follow the course timeline and the subsequent effect on their academic performance. I will also discuss some on-going work and future research directions, such as the role of learning analytics in addressing the attainment gap of ethnic minority students, and outlier detection for time-on-task estimation.
This event occurred on January 17, from 12:30 until 1:30 pm, in the LINK Research Lab (246 Nedderman Hall). It was sponsored by the Center for Research on Teaching and Learning Excellence and the LINK Research Lab.
Quan Nguyen, Ph.D.
I am a Postdoctoral Research Fellow in Educational Data Science at the School of Information, University of Michigan. My research lies at the intersection of educational psychology and data science. My work focuses on exploring learning behavioral patterns of students by analysing their digital traces to understand 1) how teachers design courses in online learning environment, 2) how learning design influences student engagement, and 3) the temporal characteristics of learning behaviors and its relation to academic performance. Prior to joining UM, I was a PhD candidate in Learning Analytics at The Open University UK and an Associate Lecturer in Applied Statistics at the University of Arts London. I had a background in Economics (BSc. & MSc.) at Maastricht University, Netherlands.
Resource Links: