Extensible Problem Specific Tutor (xPST) : Easy authoring of intelligent tutoring systems

Simple item page
dc.contributor.advisor Vasant Honavar
dc.contributor.advisor Stephen Gilbert
dc.contributor.author Kodavali, Sateesh Kumar
dc.contributor.department Computer Science
dc.date 2018-08-11T07:21:19.000
dc.date.accessioned 2020-06-30T02:38:37Z
dc.date.available 2020-06-30T02:38:37Z
dc.date.copyright Fri Jan 01 00:00:00 UTC 2010
dc.date.embargo 2013-06-05
dc.date.issued 2010-01-01
dc.description.abstract <p>An Intelligent Tutoring System (ITS) is an artificially intelligent educational software application that teaches a user skills by giving personalized feedback as the user completes tasks within a problem domain. Despite their popularity, authoring these systems is a labor-intensive process, requiring many different skill sets. A major component of an ITS is the cognitive model. Historically its implementation has required not only cognitive science knowledge, but also programming knowledge as well. To address this challenge, the Extensible Problem Specific Tutor (xPST) was developed for easy authoring of ITSs for existing software and websites. This work develops an xPST authoring tool to simplify the process of xPST authoring by the end user and to help conduct research experiments. It also evaluates the xPST system in terms of the time taken by the users to author successful models. This work also extends xPST framework to enable the creation of generalized tutors in addition to problem specific tutors. To help non-technical military trainers create xPST tutors in game scenarios, this work develops a Torque xPST Driver plugin to enable xPST authoring in Torque 3D game and evaluates authoring in spatial environment scenarios like 3D games using the authoring tool. Finally, this work compares xPST and Cognitive Tutor SDK (another authoring framework) using a fraction addition study and shows that the ratio of training development time to training experience time using xPST is approximately 50% less that that of using Cognitive Tutor SDK. This thesis also shows that there is no significant difference between the “beginner programmer” and “experienced programmer” groups in terms of the time taken to author the tasks using xPST.</p>
dc.format.mimetype application/pdf
dc.identifier archive/lib.dr.iastate.edu/etd/11849/
dc.identifier.articleid 2887
dc.identifier.contextkey 2808085
dc.identifier.doi https://doi.org/10.31274/etd-180810-425
dc.identifier.s3bucket isulib-bepress-aws-west
dc.identifier.submissionpath etd/11849
dc.identifier.uri https://dr.lib.iastate.edu/handle/20.500.12876/26055
dc.language.iso en
dc.source.bitstream archive/lib.dr.iastate.edu/etd/11849/Kodavali_iastate_0097M_11635.pdf|||Fri Jan 14 18:59:41 UTC 2022
dc.subject.disciplines Computer Sciences
dc.subject.keywords easy authoring
dc.subject.keywords intelligent tutoring systems
dc.subject.keywords ITS
dc.subject.keywords xPST
dc.title Extensible Problem Specific Tutor (xPST) : Easy authoring of intelligent tutoring systems
dc.type article
dc.type.genre thesis
dspace.entity.type Publication
relation.isOrgUnitOfPublication f7be4eb9-d1d0-4081-859b-b15cee251456
thesis.degree.level thesis
thesis.degree.name Master of Science
File
Original bundle
Now showing 1 - 1 of 1
Name:
Kodavali_iastate_0097M_11635.pdf
Size:
3.3 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Theses and Dissertations