Translation of Overlay Models of Student Knowledge for Relative Domains Based on Domain Ontology Mapping

  • Authors:

  • Sergey Sosnovsky;Peter Dolog;Nicola Henze;Peter Brusilovsky;Wolfgang Nejdl

  • Affiliations:

  • School of Information Sciences, University of Pittsburgh, USA;Department of Computer Science, Information Systems Unit, Aalborg University, Denmark;L3S Research Center, University of Hannover, Germany, sas15@pitt.edu, dolog@cs.aau.dk, henze@l3s.de, peterb@pitt.edu, nejdl@l3s.de;School of Information Sciences, University of Pittsburgh, USA;L3S Research Center, University of Hannover, Germany, sas15@pitt.edu, dolog@cs.aau.dk, henze@l3s.de, peterb@pitt.edu, nejdl@l3s.de

  • Venue:
  • Proceedings of the 2007 conference on Artificial Intelligence in Education: Building Technology Rich Learning Contexts That Work
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

The effectiveness of an adaptive educational system in many respects depends on the precision of modeling assumptions it makes about a student. One of the well-known challenges in student modeling is to adequately assess the initial level of student's knowledge when s/he starts working with a system. Sometimes potentially handful data are available as a part of user model from a system used by the student before. The usage of external user modeling information is troublesome because of differences in system architecture, knowledge representation, modeling constraints, etc. In this paper, we argue that the implementation of underlying knowledge models in a sharable format, as domain ontologies-along with application of automatic ontology mapping techniques for model alignment-can help to overcome the “new-user” problem and will greatly widen opportunities for student model translation. Moreover, it then becomes possible for systems from relevant domains to rely on knowledge transfer and reuse those portions of the student models that are related to overlapping concepts.