Declarative to Procedural Tutors: A Family of Cognitive Architecture-based Tutors

Ritter1, F., Yeh, K.1, Cohen, M.2, Weyhrauch, P.3, Kim, J.4, and Cao, C.5

Proceedings of the 22nd Annual Conference on Behavior Representation in Modeling and Simulation (BRiMS), Ottawa, Canada (July 2013)

We have created a tutoring architecture, D2P (Declarative to Procedural), based on ACT-R’s theory of knowledge and learning for declarative and procedural memory. D2P also draws on general theories of leaarning and a recent review by Kim, Ritter, and Koubek (in press). D2P provides multimedia instruction pages followed by questions, video, and/or simulations to test and proceduralise the declarative knowledge. It is implemented in XML, XML-based tools, Java, and COTS tools. We have created the two D2P tutors. We have evaluated one, and it has a 1.48 effect size of learning how much to lead. We have found that modern tools help create a tutoring system; creating a tutoring architecture requires more than just the system (such as manuals and example systems); and the next steps are to test the theory of learning and use a cognitive architecture-based knowledge to make the system adaptive.

1 Department of Computer Science and Engineering, Pennsylvania State University
2 Department of Computer Science, Massachusetts College of Liberal Arts
3 Charles River Analytics
4 Department of Psychology, University of Central Florida
5 Department of Computer Science, University of Massachusetts Amherst

For More Information

To learn more or request a copy of a paper (if available), contact Peter Weyhrauch.

(Please include your name, address, organization, and the paper reference. Requests without this information will not be honored.)