报告题目：Developing Usable, Useful, and Pervasive Learning Analytics for All
报告人：Shin’ichi Konomi 教授
Shin’ichi Konomi is a Professor and Director of Learning Analytics Center at the Faculty of Arts and Science, and a Professor at School of Interdisciplinary Science and Innovation, Kyushu University. He received his Ph.D. degree in Computer Science from Kyoto University in 1996, and M. Eng. degree in Computer Science and Communication Engineering from Kyushu University. Before joining Kyushu University in 2017, he was an associate professor at the University of Tokyo, a senior research associate at the University of Colorado at Boulder, and a postdoctoral research scientist at GMD (German National Research Centre for Information Technology with eight institutes in three different cities; since 2001 merged with Fraunhofer Society). He conducts research based on human-centric and data-centric approaches to develop novel computational environments that make people smarter and happier. He is a member of ACM, IEEE, IEICE, IPSJ, DBSJ, and GIS Association of Japan.
As smart technologies pervade our everyday environments, they change what people should learn to live and work meaningfully as indispensable participants of our society. For instance, ubiquitous availability of smart devices and communication networks may reduce the burden for people to remember factual information. At the same time, it may increase the importance of the skills and knowledge to live, work, collaborate, and create effectively in the technology-pervaded world. In the midst of such a social and technological shift, we have initiated our major efforts to develop technological support environments for older learners in the rapidly aging society of Japan. This talk will introduce the ideas and initial experiences of the efforts in the context of a JST (Japan Science and Technology Agency) project, and discuss general opportunities and challenges of future learning technologies for all. Our approach to developing effective learning-support systems and services for all, including older adults, is based on learning analytics. We have thus developed user interfaces and conducted experiments to realize proper environments for the measurement, collection, analysis and reporting of data about older learners and their contexts, for purposes of understanding and optimizing learning and the environments in which it occurs. In particular, we developed a system for multimodal learning analytics using eye-tracker and EEG measurement, and a dual-tablet user interface that allows older learners to interact with learning analytics environments easily without the cognitive burden imposed by the complexity of conventional GUI-based interactions. Finally, we briefly discuss a distributed learning support environment that considers limited internet access in developing and/or rural communities with the high ratio of older population.