Abstract: This talk will introduce a cutting-edge technology innovation, PASTEL, for the next generation adaptive instruction in online courseware. PASTEL is a suite of AI-based learning engineering methods to evidence-basedly create adaptive online courseware on an existing MOOC platform (e.g., Coursera, edX, etc.). PASTEL includes (1) a text-mining method to analyze courseware content to identify latent constructs, (2) a prediction method to identify students at risk and provide proactive scaffolding to prevent unproductive failure, (3) a web-based authoring method for cognitive tutors and their seamless integration to the online courseware, (4) an evidence-based courseware-content validation method as an application of reinforcement learning with students’ performance and learning data, and (5) a method for automatic question generation as an application of deep learning to instructional text on the online courseware. I will also introduce an instance of adaptive online courseware, called CyberBook, built by PASTEL on Open edX. We will then discuss research opportunities for innovative AI applications in education and the sciences of learning with PASTEL and CyberBook.

Short Bio: Dr. Noboru Matsuda is an Associate Professor of Cyber STEM Education in the Department of Teaching, Learning and Culture at Texas A&M University. Noboru’s research interests include innovations of cutting-edge AI technologies to enhance learning and advance theories in the sciences of learning.

Noboru received an MS in Math Education from Tokyo Gakugei University (Tokyo, Japan) and a Ph.D. in Intelligent Systems from the University of Pittsburgh. He then received postdoctoral research training at the Human-Computer Interaction Institute at Carnegie Mellon University. Noboru has developed a number of intelligent tutoring systems and conducted applied research for educational data mining mainly in the STEM subject fields.

Noboru is currently the director of the Innovative Educational Computing Laboratory. He has received 6 federal grants totaling approximately $5M from NSF and the US Department of Education (IES) in the last 13 years, where he served as a PI on 5 proposals.

Noboru has been leading the SimStudent project (www.SimStudent.org) where the research team developed an artificial intelligence that can learn problem-solving skills through guided-problem solving (aka peer tutoring). In recent years, Noboru has launched a new research project on evidence-based learning engineering, called PASTEL, where he and his colleagues study how to efficiently build adaptive online courses (called CyberBook) and how to develop research on AI in education and the sciences of learning using PASTEL and CyberBook.

Noboru loves programming and swimming when he is not dreaming of the future of technology enhanced education.