Adaptivity in learning technologies: Kinds, effectiveness, and authoring
Associate Prof. Vincent Aleven
Date: Thursday 15 September 2016 - 15:30-16:30
Room: Auditorium Malraux
Vincent Aleven is an associate professor in the Human-Computer Interaction Institute at Carnegie Mellon University with 20 years of experience in interdisciplinary research in the area of Artificial Intelligence in Education (AIED). He has worked on educational software based on cognitive theory and self-regulated learning theory. He and colleagues have created effective non-programmer authoring tools for intelligent tutoring systems and have created tutoring systems that support individual and collaborative learning, often in areas of mathematics, that have turned out to be practical and effective in actual classrooms. Aleven has over 200 publications to his name. He and his colleagues and students have won 7 best paper awards at international conferences. He is the co-editor-in-chief of the International Journal on Artificial Intelligence in Education. He is or has been PI on 8 major research grants and co-PI on 10 others.
Abstract. What is adaptivity in learning technologies and what kinds of adaptivity have turned out to be effective in enhancing educational outcomes? To answer this question, I present an “Adaptivity Grid” that provides a framework for thinking about what adaptivity means. Using the framework to organize empirical results from the literature, I identify what kinds of adaptivity have been most successful and I identify trends in current research. I then turn to the question: How can adaptive learning technologies be authored easily to support widespread use? I address this question in the context of intelligent tutoring systems, a form of adaptive learning technologies proven to be highly effective. Specifically, I report on my experience in 12+ years of research and development on the Cognitive Tutor Authoring Tools (CTAT). The Adaptivity Grid helps identify good opportunities for extending authoring tools.
Orchestrating Robots: How does learning technology research inform the design of educational robots?
Prof. Pierre Dillenbourg
Date: Thursday 15 September 2016 - 9:00-10:00
Room: Auditorium Malraux
A former teacher in elementary school, Pierre Dillenbourg graduated in educational science (University of Mons, Belgium). He started his research on learning technologies in 1984. He obtained a PhD in computer science from the University of Lancaster (UK), in the domain of artificial intelligence applications for educational software. He has been assistant professor at the University of Geneva. He joined EPFL in 2002. He is currently full professor in learning technologies in the School of Computer & Communication Sciences, where he is the head of the CHILI Lab: "Computer-Human Interaction for Learning & Instruction ». He is also the academic director of Center for Digital Education, which implements the MOOC strategy of EPFL. EPFL recently passed over 1 million MOOC registrations. He recently wrote a book entitled "Orchestration Graphs" that proposes a formal language for instructional design (EPFL Press).
Abstract. The use of robots in education has recently experienced a sudden rise. Many of these robots are small programmable moving devices aimed at learning programming and robotic-related topics such as sensors. This approach has great synergies with the makers movement. Other education robots are small humanoids, playing various roles (co-learner, teacher, student,…), which have recently become affordable. This research has been inspired by the work on human-robot interaction (HRI), e.g. capturing and rendering emotions. In addition to HRI, TEL research provides useful knowledge to the designers of robotic activities. A main TEL lesson is that the learning output does not simply depend on the smoothness of interaction, but mainly upon the learning activities in which the learner and the robot jointly engage, including demanding activities. Cognitive load is a condition for learning! A second lesson comes from the work on classroom orchestration, which showed that usability does not come from one-to-one interaction, but from the efforts required from the teacher managing TEL activities (the so-called ‘classroom usability’). This research has revealed for instance the value of paper-based interfaces. Logistics pitfalls may spoil the most wonderful learning scenario! I will illustrate this transfer from TEL to education robotics by some of our projects on classroom robots.
European R&I and digital learning - overview and orientations
Date: Thuesday 13 September 2016 - 18:00-19:00
Room: Auditorium Malraux
Liina Munari is a Senior Programme Officer in the Unit G3 "Learning, Multilinguism and Accessibility" of the DG CONNECT, European Commission. She has been working as an EU civil servant in different the EU institutions since 1997.
She joined the European Commission in 2006 to work at the EU R&I programme and has been involved in learning technologies part of the programme since 2011. Her academic background is in European and international politics.