Temporary Belief Sets Management in Adaptive Training Systems

  • Robert Andrei Buchmann
  • Anamaria Szekely
  • Delia Pulcher
Part of the Lecture Notes in Business Information Processing book series (LNBIP, volume 97)


The paper proposes a semantic view on the notion of ,,learning object” and an application model based on RDF-based learning objects and learning processes. Direct feedback is individualized for test subjects and learning tasks, according to requirements defined for corporate training. The knowledge model allows contextualization and subjectivity, which, in turn, are used to dynamically generate temporary belief sets, compare them to the (theoretically) objective belief set underlying the learning content and adapt learning recommendations to each particular user. The semantic models also determine learning prerequisites and the screen flow adapted to each individual learner, thus influencing usability.


Learning object qualified knowledge context RDF SPARQL 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    The Resource Description Framework,
  2. 2.
    Höver, K.M., Steiner, C.M.: Adaptive Learning Environments: A Requirements Analysis in Business Settings. International Journal of Advanced Corporate Learning 2(3), 27–33 (2009)Google Scholar
  3. 3.
    Beck, R.: What are Learning Objects?,
  4. 4.
    Berners-Lee, T., Hendler, J., Lassila, O.: The Semantic Web. Scientific American 284(5), 34–43 (2001)CrossRefGoogle Scholar
  5. 5.
    Moodle – the Official Website,
  6. 6.
    Blackboard – the Official Website,
  7. 7.
    The Web Ontology Language,
  8. 8.
  9. 9.
    Gonzalez-Videgaray, M., Hernandez-Zamora, G., del Rio-Martinez, J.H.: Learning Objects in Theory and Practice: A Vision from Mexican University Teachers. Journal Computers & Education 53(4), 1330–1338 (2009)CrossRefGoogle Scholar
  10. 10.
    The IEEE Learning Object Metadata Standard,
  11. 11.
    Bennacer, N., Bourda, Y., Doan, B.: Formalizing for Querying Learning Objects Using OWL. In: Looi, C.T., Sutinen, E., Sampson, D.G., Aedo, I., Uden, L., Kähkönen, E. (eds.) Proceedings of the IEEE International Conference on Advanced Learning Technologies, ICALT 2004, pp. 321–325. IEEE Computer Society, Washington (2004)CrossRefGoogle Scholar
  12. 12.
    Bouzeghoub, A., Defude, B., Ammour, S., Duitama, J.F., Lecocq, C.: A RDF Description Model for Manipulating Learning Objects. In: Looi, C.T., Sutinen, E., Sampson, D.G., Aedo, I., Uden, L., Kähkönen, E. (eds.) Proceedings of the IEEE International Conference on Advanced Learning Technologies, ICALT 2004, pp. 81–85. IEEE Computer Society, Washington (2004)CrossRefGoogle Scholar
  13. 13.
    Ahmed, S., Parsons, D., Ryu, H.: Supporting Adaptive Learning Interactions with Ontologies. In: Ryu, H., Champion, E. (eds.) Proceedings of the 11th International Conference of the NZ Chapter of the ACM Special Interest Group on Human-Computer Interaction, pp. 17–24. ACM Press, New York (2010)Google Scholar
  14. 14.
    Jovanovic, J., Gasevic, D., Devedzic, V.: TANGRAM for Personalized Learning Using the Semantic Web Technologies. Journal of Emerging Technologies in Web Intelligence 1(1), 6–21 (2009)CrossRefGoogle Scholar
  15. 15.
    Open RDF Official Website,
  16. 16.
    OWLIM Official Website,
  17. 17.
    SPARQL Official Website,
  18. 18.
    The Serialization of SPARQL Query Results in JSON,
  19. 19.
    Allemang, D., Hendler, J.: Semantic Web for the Working Ontologist. Morgan Kaufmann, San Francisco (2008)Google Scholar
  20. 20.
  21. 21.
    Defining N-ary Relations on the Semantic Web,
  22. 22.

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Robert Andrei Buchmann
    • 1
  • Anamaria Szekely
    • 1
  • Delia Pulcher
    • 1
  1. 1.Faculty of Economic Sciences and Business Administration, Business Information Systems Dpt.Babes Bolyai UniversityCluj NapocaRomania

Personalised recommendations