Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/13837
Title: Decision-theoretic intelligent tutoring system
Authors: PEK PENG KIAT
Keywords: Adaptive Tutoring, Bayesian Network, Dynamic Decision Network, Learning Values, Student Model, Tutoring Policy
Issue Date: 2-May-2004
Source: PEK PENG KIAT (2004-05-02). Decision-theoretic intelligent tutoring system. ScholarBank@NUS Repository.
Abstract: This thesis demonstrates that decision-theoretic pedagogical action selection is robust because of sound probabilistic reasoning and defensible decision. The student model is explicitly represented by a set of Bayesian networks. The automated diagnostic capability is enhanced by including item selection. Since tutoring requires more than one action, Bayesian network is extended to represent temporal probability model. By formulating utility functions in term of learning values and behaviour factors, personalised tutoring policy can always be generated in polynomial time. Evaluations of iTutor, a prototype decision-theoretic tutoring system, have validated that adaptive tutoring facilitates studenta??s learning in the most effective and efficient manner.
URI: http://scholarbank.nus.edu.sg/handle/10635/13837
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
PekPK.pdf3.77 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

347
checked on Dec 11, 2017

Download(s)

282
checked on Dec 11, 2017

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.