Interacting with Inspectable Bayesian Student Models

Article type: Research Article

Authors: Zapata-Rivera, Juan-Diego | Greer, Jim E.

Affiliations: ARIES Laboratory, Department of Computer Science, University of Saskatchewan, Saskatoon, Canada. Diego.Zapata@usask.ca, greer@cs.usask.ca; http://www.cs.usask.ca/research/research_groups/aries/

Abstract: Inspectable student models focus on the idea of letting students and teachers interact with the representation of the student that the system maintains. Both humans and the system can benefit from this interaction. By externalizing the student model and making it an object for inspection, several representational and interaction issues arise. This paper presents ViSMod (Visualization of Bayesian Student Models) an integrated tool to visualize and inspect distributed Bayesian student models. Using ViSMod, students and teachers can understand, explore, inspect, and modify Bayesian student models. ViSMod offers a practical tool that helps students and teachers to engage in negotiated assessment processes. Student models in ViSMod follow the Bayesian belief net backbone structure proposed by Reye (1996), which describes both cognitive and social aspects of the student. In addition, we report on a usability study of the ViSMod tool and an exploratory study focused on the effects of employing various levels of guidance and support in the way students interact with inspectable Bayesian student models.

Journal: International Journal of Artificial Intelligence in Education, vol. 14, no. 2, pp. 127-163, 2004