Modeling the Learner in 4-D
Abstract: In recent years, student modeling research has increasing moved from modeling what a student knows to modeling a broader range of dimensions of the student, including engagement, affect, and meta-cognition. In this talk, I discuss my group's recent work to model students in a more multi-dimensional fashion, including our recent work to predict whether a student has achieved robust learning that prepares them for future learning. I discuss the additive benefits of modeling learners along multiple dimensions. I will conclude with a discussion of "discovery with models" analyses that our research has produced, expanding basic understanding of human learning, and the possibilities for richer and more flexible adaptive personalization created by these developments.
Bio: Ryan S. J. d. Baker is Assistant Professor of Psychology and the Learning Sciences at Worcester Polytechnic Institute, with a collaborative appointment in Computer Science. As of September 2012, he will be the Julius and Rosa Sachs Distinguished Lecturer at Teachers College Columbia University. He graduated from Carnegie Mellon University in 2005, with a Ph.D. in Human-Computer Interaction, and was a Post-Doctoral Fellow at Carnegie Mellon and the University of Nottingham, and first Technical Director of the Pittsburgh Science of Learning Center DataShop. In the summer of 2011, he was elected founding President of the International Educational Data Mining Society. He is Associate Editor of the Journal of Educational Data Mining. His scientific articles have won four awards, and have been nominated for eight others.
Contextualizing Useful Recommendations
Abstract: Recommender Systems (RSs) are now popular tools and techniques providing suggestions for items to be of use to a user. RSs narrow down the overwhelming amount of information and choices available today on the Web by predicting what items are more likely to be interesting to the user. They track users’ actions that signal their preferences, and aggregate them into predictive (user) models. State of the art user models still cannot fully explain and predict the needs of the user while is searching for new items. In fact, the specific ephemeral needs of the user, the context of the search, and the context of items’ usage, do influence the user’s response to and evaluation for items. Hence, RSs should take into account this information to deliver more useful (perceived) recommendations. Context modeling and context-dependent reasoning is a complex subject and there are still major technical and practical difficulties to solve: obtain sufficient and reliable data describing the user preferences in context; selecting the right context information, i.e., relevant in a particular personalization task; understanding the impact of the contextual dimensions on the user decision making process; embedding the contextual dimensions in a recommendation computational model. These topics will be illustrated in the talk, making examples taken from the recommender systems that we have developed.
Bio: Francesco Ricci is an associate professor of computer science at the Free University of Bozen-Bolzano, Italy. His current research interests include recommender systems, intelligent interfaces, mobile systems, machine learning, case-based reasoning, and the applications of ICT to tourism. He has published more than one hundred of academic papers on these topics. He is on the editorial board of Journal of Information Technology and Tourism and the Journal of User Modeling and User Adapted Interaction. He is member of the steering committee of the ACM Conference on Recommender Systems. He served on the program committees of several conferences, including as a program co-chair of the ACM Conference on Recommender Systems (RecSys), the International Conference on Case-Based Reasoning (ICCBR) and the International Conference on Information and Communication Technologies in Tourism (ENTER).