Inspectable Bayesian student modelling servers in multi-agent tutoring systems

  • Authors:
  • Juan-Diego Zapata-Rivera;Jim Greer

  • Affiliations:
  • ARIES Lab, Department of Computer Science, University of Saskatchewan, Saskatoon, Saskatchewan, Canada;ARIES Lab, Department of Computer Science, University of Saskatchewan, Saskatoon, Saskatchewan, Canada

  • Venue:
  • International Journal of Human-Computer Studies
  • Year:
  • 2004

Quantified Score

Hi-index 0.00

Visualization

Abstract

User modelling shells and learner modelling servers have been proposed in order to provide reusable user/student model information over different domains, common inference mechanisms, and mechanisms to handle consistency of beliefs from different sources. Open and inspectable student models have been investigated by several authors as a means to promote student reflection, knowledge awareness, collaborative assessment, self-assessment, interactive diagnosis, to arrange groups of students, and to support the use of students' models by the teacher. This paper presents SModel, a Bayesian student modelling server used in distributed multi-agent environments. SModel server includes a student model database and a Bayesian student modelling component. SModel provides several services to a group of agents in a CORBA platform. Users can use ViSMod, a Bayesian student modelling visualization tool, and SMV, a student modelling database viewer, to visualize and inspect distributed Bayesian student models maintained by SModel server. SModel has been tested in a multi-agent tutoring system for teaching basic Java programming. In addition, SModel server has been used to maintain and share student models in a study focussed on exploring the existence of student reflection and analysing student model accuracy using inspectable Bayesian student models.