The field of EDM: where we came from and where we're going
Abstract: The Educational Data Mining community has undergone tremendous growth in the past decade. This talk will discuss how we got to where we are, as well as upcoming challenges for the field. The beginning of the EDM workshop series grew out of the AIED and ITS conferences, which greatly influenced both the initial participants and the frameworks used for viewing data mining problems. The development of the EDM conference series served to focus the field, and greatly increase the range of participants. Although much progress has been made in the past 6 years, there remain some large challenges not (yet) well addressed by the EDM community. Two issues include who are the consumers for the advances that we make, and under what conditions can we draw scientific conclusions from data-mining activities.
Short biography: Joseph Beck, assistant professor of Computer Science, has been at WPI since 2007. His research focuses on educational data mining, a new discipline that develops techniques for analyzing large educational data sets to make discoveries that will improve teaching and learning. His work centers on estimating how computer tutors impact learning. He established the first workshop in the field and in 2008 was program co-chair of the first International Conference on Educational Data Mining. He holds a BS in mathematics, computer science, and cognitive science from Carnegie Mellon University, and a PhD in computer science from the University of Massachusetts, Amherst.
Generative Adaptivity for Optimization of the Learning Ecosystem
Abstract: Most of the current work on improving learning outcomes focuses on a small subset of variables of an immensely multi-dimensional space of the learning ecosystem. With ITS, learning games, and other digital content we consider only individual students, other research focuses only on teacher development, or only on curriculum improvement. In this talk I will describe our efforts on how to discover optimal parameters of this system that considers student factors (engagement and mastery), classroom factors (blended learning variations and group learning variations), curriculum factors (multidimensional variation of existing curricula), and teacher factors (in-class tools that mitigate weaknesses, and promote teacher development). I will describe our work on algorithms to discover optimal learning pathways in this high-dimensional space. I will conclude with recent remarkable outcomes of deploying a portion of our platform on algebra challenges conducted on two US states and the country of Norway.
Short biography: Zoran Popovic is a Director of Center for Game Science at University of Washington and founder of Engaged Learning. Trained as a computer scientist his research focus is on creating interactive engaging environments for learning and scientific discovery. His laboratory created Foldit, a biochemistry game that produced three Nature publications in just two years, an award-winning math learning games played by over five million learners worldwide. He is currently focusing on engaging methods that can rapidly develop experts in arbitrary domains with particular focus on revolutionizing K-12 math education. His Algebra Challenges conducted in Washington, Minnesota, and Norway, have shown that more than 93% of children even in elementary school can learn key algebra concepts in 1.5 hours. He has recently founded Engaged Learning to apply his work on generative adaptation to any curricula towards the goal of achieving school mastery by 95% of students. His contributions to the field of interactive computer graphics have been recognized by a number of awards including the NSF CAREER Award, Alfred P. Sloan Fellowship and ACM SIGGRAPH Significant New Researcher Award.
150K+ online students at a time: How to understand what's happening in online learning
Abstract: Many MOOCs have had more that 100K students register for their courses, with many completing, but many dropping out. Is this the future of online education? Should we worry about attrition, or is this a new, natural, and expected trend in online learning? More importantly, how can we come to understand the (new) student experience? In the past year we have run several MOOCs with more than 350K registrants (and then another 250K who have taken the MOOC without the synchronous class structure). Learning in MOOCs is rather different than traditional learning experiences, and now we have the tools to start to understand how and why those differences exist. However, analytics often miss important behaviors that are key to understanding the inner life of the online student. I'll discuss the boundaries between EDM and observational methods that reveal the social community of learners that are essential for making MOOCs succeed, and what seems to work (and not work) in MOOCs.
Short biography: Daniel Russell is the Über Tech Lead for Search Quality and User Happiness in Mountain View. He earned his PhD in computer science, specializing in Artificial Intelligence until he realized that magnifying human intelligence was his real passion. Twenty years ago he foreswore AI in favor of HI, and enjoys teaching, learning, running and music, preferably all in one day. His MOOCs have helped students become much more effective online searchers. His online course, PowerSearchingWithGoogle.com has had ~500K students go through the content, meaning that somewhere on earth, a video of him teaching search skills has been on-screen for more than 200 years.