Chair: Prof. Nancy LAW, Faculty of Education, The University of Hong Kong
The term "learning analytics" is getting more attention in the education literature. This seminar gives an introduction to the MOOC-Learner project at the Computer Science and Artificial Intelligence Laboratory (CSAIL) at MIT that is designed to provide tools for teachers, instructional designers and education researchers to obtain some "learning analytics" from their students' learning data. Each time a learner engages with an e-learning system we can log the interaction. Data comprising mouse clicks, video controls, problem responses, programs, etc. then becomes available to learning science. The MOOC-Learner-Project's goal is to use this data to provide insights into how students learn and how instructors can effectively teach. The challenge is to provide technology and develop new approaches that transforms this fundamentally different set of observations into actionable knowledge.
In this talk we the present the general concept and approach that the MOOC Learner project takes to supporting the wider education community to employ data analytics tools for learning analytics. As an illustration we present two use-cases: the relationship between the doer effect and learning computational subjects and what behavior affects the dropout of students.
Dr. Erik Hemberg is a research scientist in the AnyScale Learning For All (ALFA) group at Massachusetts Institute of Technology (MIT) Computer Science and Artificial Intelligence Laboratory (CSAIL). ALFA focuses on scalable machine learning, data science, and evolutionary algorithms. His award-winning research spans algorithms applied in clinical medicine knowledge discovery, law, cyber security and MOOC technology. He developed a blended Learning course at Shantou University and a computer science outreach course at University College Dublin. He has also created and provided e-learning software for a business school in Sweden.