Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Evaluating the inference mechanism of adaptive learning systems

: Weibelzahl, S.; Weber, G.


Brusilovsky, P.; Corbett, Albert; Rosis, Fiorella de:
User Modeling 2003. 9th International Conference, UM 2003 : Johnstown, June 22 - 26, 2003. Proceedings
Berlin: Springer, 2003 (Lecture Notes in Artificial Intelligence 2702)
ISBN: 3-540-40381-7
ISSN: 0302-9743
pp.154-162 : Ill., Lit.
International Conference on User Modeling (UM) <9, 2003, Johnstown>
Conference Paper
Fraunhofer IESE ()
empirical evaluation; inference; User Modeling; user behavior; testing

The evaluation of user modeling systems is an important though often neglected area. Evaluating the inference of user properties can help to identify failures in the user model. In this paper we propose two methods to assess the accuracy of the user model. The assumptions about the user might either be compared to an external test, or might be used to predict the users' behavior. Two studies with five adaptive learning courses demonstrate the usefulness of the approach.