Authors:
Rina Azoulay
1
;
Esther David
2
;
Dorit Hutzler
1
and
Mireille Avigal
3
Affiliations:
1
Jerusalem College of Technology, Israel
;
2
Ashkelon Academic College, Israel
;
3
The Open University of Israel, Israel
Keyword(s):
Intelligent Tutoring Systems, Reinforcement Learning, Bayesian Inference.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Computational Intelligence
;
Evolutionary Computing
;
Knowledge Discovery and Information Retrieval
;
Knowledge-Based Systems
;
Machine Learning
;
Soft Computing
;
Symbolic Systems
Abstract:
The main challenge in developing a good Intelligent Tutoring System (ITS) is suit the difficulty level of questions and tasks to the current student's capabilities. According to state of the art, most ITS systems use the Q-learning algorithm for this adaptation task. Our paper presents innovative results that compare the performance of several methods, most of which have not been previously applied for ITS, to handle the above challenge. In particular, to the best of our knowledge, this is the first attempt to apply the Bayesian inference algorithm to question level matching in ITS. To identify the best adaptation scheme based on this groundwork research, for the evaluation phase we used an artificial environment with simulated students. The results were benchmarked with the optimal performance of the system, assuming the user model (abilities) is completely known to the ITS. The results show that the best performing method, in most of the environments considered, is based on a Baye
sian Inference, which achieved 90% or more of the optimal performance. Our conclusion is that it may be worthwhile to integrate Bayesian inference based algorithms to adapt questions to a student's level in ITS. Future work is required to apply these empirical results to environments with real students.
(More)