Design-Deploy-Data-Discover: A Technology-Based Continuous Feedback Loop to Improve Learning Science and Education

Speaker
Kenneth Koedinger
Professor, Human-Computer Interaction Institute, Carnegie Mellon University

When
-

Where
Newell-Simon Hall 1305 (Michael Mauldin Auditorium)

Description

Educational technologies are being increasingly used in schools and colleges. Well-designed systems go beyond the support provided by teachers and textbooks to assess students as they work, adapt instruction to their individual needs, and provide stakeholders with detailed reports on students’ strengths and weaknesses. Further, widely-deployed systems provide a powerful research platform for data collection and experimentation to advance theories of knowledge, learning, and instruction.

I will focus on methods of Cognitive Task Analysis (CTA) and their use in developing better theories of academic knowledge acquisition and in designing improved instruction. In addition to our math Cognitive Tutors, a recent demonstration of the power of CTA-driven course design comes from a study of the CMU OLI on-line statistics course materials, which have been shown to contribute to better student outcomes in half of the time! One goal of the Pittsburgh Science of Learning Center is to create an n e-science infrastructure that helps to automate CTA and so discover better cognitive models and fuel better instructional design. A key strategy we are pursuing is a mixed initiative human-machine discovery process whereby data (and model) visualizations enhance feature discovery by humans which in turn enhance model discovery by machines.

Speaker's Bio

I have an MS in Computer Science, a PhD in Cognitive Psychology, and experience teaching in an urban high school. This multidisciplinary background supports my research goals of understanding human learning and creating educational technologies that increase student achievement. I have developed computer models of student thinking and learning that are used to guide the design of educational materials, practices and technologies. These cognitive models provide the basis for an approach to educational technology called “Cognitive Tutors”. My colleagues and I have developed Cognitive Tutors for mathematics, science, and language and have tested them in the laboratory and as part of real courses. In a whole-year classroom study with our Algebra Cognitive Tutor, we found that students in our experimental classes outperformed students in control classes by 50–100% on targeted real world problem solving skills and by 10–25% on standardized tests. My research has contributed new principles and techniques for the design of educational software and has produced basic cognitive science research results on the nature of mathematical thinking and learning. I have authored 126 peer-reviewed publications, 10 book chapters, and 59 other papers and have been a Project Investigator on 16 major grants. I am a co-founder and board member of Carnegie Learning, Inc. and the CMU Director of the Pittsburgh Science of Learning Center. The center leverages computational approaches to identify the instructional conditions that cause robust student learning. The center started in 2004 and is funded by the National Science Foundation for $5 million per year until 2014.