Lecture Title: Learning Analytics at Scale: How MOOCs Enable Educational Data Science
Speaker: Christopher Brooks, University of Michigan
Abstract: Spurred on by the general availability of data mining and machine learning as well as a deluge of fine grained tracking data available in large scale learning environments, the last decade has seen the emergence of the field of Educational Data Science. In this talk, I will discuss the impact of the Massive Open Online Course (MOOC) movement on this field, focusing specifically on how I have engaged in(a) discourse analysis (b) predictive modelling, (c) randomized controlled experimentation, and (d) participatory crowd design to better understand learners and empower their learning. With over 6 million enrolled learners and more than one hundred MOOC offerings, the University of Michigan offers one of the largest online learning experiment platforms, diverse both in the courses offered and the learners served. I will conclude the talk with a brief vision of the future this space holds, and a lay out a roadmap for the coming age of adaptive scaled learning environments.
Biography: Christopher Brooks is a Research Assistant Professor in the School of Information, and Director of Learning Analytics and Research at the Office of Academic Innovation at the University of Michigan. He is a Computer Scientist by background, and his work focuses on leveraging and supporting the diversity of students and their interactions in large scale online learning environments (e.g. MOOCs). His efforts include building models of educational discourse, predictive models of student success, and scaled replication infrastructure for educational data science. He teaches several large courses in the Applied Data Science with Python specialization on the Coursera platform.
For additional information, please contact Eyal deLara at delara@cs.toronto.edu