Adaptive Assistance for Peer Tutoring (Walker, Rummer, Koedinger)

From LearnLab
Revision as of 15:20, 14 April 2008 by Erin-Walker (Talk | contribs)

Jump to: navigation, search

Collaborative Extensions to the Cognitive Tutor Algebra: Adaptive Assistance for Peer Tutoring

Erin Walker, Nikol Rummel, and Ken Koedinger

Summary Tables

PI Erin Walker
Co-PIs Nikol Rummel, Ken Koedinger


Our research goal is to integrate a peer tutoring script within the context of the Cognitive Tutor Algebra (CTA) allowing students to tutor each other through the interface of an intelligent tutoring system (ITS) that provides both domain support and collaborative tutoring. In the PSLC project, “Collaborative Extensions to the Cognitive Tutor Algebra: A Peer Tutoring Addition,” we have added peer tutoring to the Cognitive Tutor Algebra and developed adaptive domain support for the peer tutor. We propose to continue this work by developing and evaluating collaborative assistance for the peer tutor within this context. This assistance will target both the skills required to successfully tutor and the motivation for students to tutor. Once we have shown fixed collaborative assistance to be effective, we plan to implement it in an adaptive fashion, and compare the effects of adaptive and fixed assistance on collaborative skill acquisition and robust domain learning.

The integration of intelligent tutoring and collaborative learning allows us to investigate the differential effects of varying the type and adaptivity of assistance provided to collaborating peers on the acquisition of collaborative skills and on robust domain learning. Further, the development of a successful adaptive collaborative learning system would be a significant contribution to the ITS community.

Background and Significance


See Peer Tutoring Glossary

Research Question

What are the differential effects of adaptive and fixed support on student collaborative process during a peer tutoring activity and the resulting robust learning outcomes?

How does an instructional method that provides metacognitive support and incentives for peer tutoring affect student collaborative process and robust learning outcomes?

Independent variables

We vary the agents involved in the interaction using the mode of instruction. For example, students may interact individually with a cognitive tutor, may interact with each other using a collaboration script, or may interact with each other with the help of a cognitive tutor.

We also plan to examine the type of assistance provided to the students. They may receive assistance to tutoring competence (either domain, metacognitive, or procedural) or motivational support.