home - login - register

PERC 2015 Abstract Detail Page

Previous Page  |  New Search  |  Browse All

Abstract Title: An Intelligent Tutoring System that Supports Conceptual Understanding of Physics
Abstract: As physics teachers know, even the best students often master the ability to solve quantitative problems, but nonetheless don't understand basic physics concepts. To address this problem, we developed Rimac, a tutoring system that engages students in natural-language dialogues about the concepts associated with just-solved problems.  Rimac's dialogues implement empirically-derived principles to guide the tutor in asking questions about the concepts associated with a problem, and the tutor's feedback on students' responses.  These principles stem from our extensive analyses of tutoring sessions between human physics teachers and students.  We describe a recent study that compared two versions of Rimac in high school physics classrooms: an experimental version that deliberately executes the tutoring principles and a control version that does not, but implements prior state-of-the-art dialogue generation practices.  Although students learned from both versions of the tutor, the experimental group outperformed the control group and was especially beneficial for female students.
Abstract Type: Contributed Poster Presentation

Author/Organizer Information

Primary Contact: Sandra Katz
Learning Research and Development Center, University of Pittsburgh
3939 O'Hara Street
Pittsburgh, PA 15260
Phone: 412-624-7054
Fax: 412-624-9149
and Co-Presenter(s)
Pamela Jordan, Patricia Albacete
Learning Research and Development Center
University of Pittsburgh