Intelligent Tutoring Systems Measuring Student Effort During Assessment

Each tutoring system must face the problem of dealing with uncertainty involved in student interactions. The quality of a correct answer to a question may be di erent for each individual student. Some answers are produced by careful thinking and anal- ysis using memorised facts, where other answers are just guesses. Therefore there is a need to develop a tutoring system which takes into consideration the quality of an answer to produce a more detailed student model. Many tutoring systems developed to this point use question-answer techniques to estimate the student knowledge state, however none of them take into consideration the quality of student answers to esti- mate a student's knowledge state. The tutoring system presented here addresses this problem by measuring student e ort during assessment. In this thesis, I present an exploratory study of eye tracking technology which is used to modify the student model in Intelligent Tutoring Systems during assessment to cre- ate a more accurate estimate of the student's knowledge state. This tutoring system uses a Bayesian Network (BN), a formal framework for uncertainty management in Arti cial Intelligence based on probability theory, to model the student's knowledge state. An extra communication channel between the student and the tutoring system is an eye tracking device which is used to obtain real-time data about the student's eye activities. Using this additional data about the student allows the ITS to create a more precise model of the student knowledge state, which at the end leads to better adaptation of the learning instructions. In addition, I describe the architecture of this tutoring system and the role of each component in the system. The tutoring system in this thesis sets an example and o ers a reference on the appli- cation of eye tracking technology in the development of intelligent tutoring systems. The tutoring system presented in this thesis can be useful to any work involving an eye tracking technology due to its ability to extract an eye movement in real time. The implementation of this tutoring system can be used as an example of communication between a tutoring system and an eye tracking device.

Name thesis:degree_name

Master of Science (MSc)

Level thesis:degree_level

Master's

Discipline thesis:degree_discipline

Computer Science

Grantor dc:publisher

Faculty of Graduate Studies and Research, University of Regina

Year dc:date.issued

2013

Author dc:creator

• Lach, Peter

Advisors dc:contributor.advisor

• Butz, Cortney J.
• Maguire, Robert

Committee member dc:contributor.committeemember

• Hepting, Daryl

Language dc:language.iso

en

DOI

https://doi.org/10.82465/3818

OAI identifier oai:identifier

oai:uregina.scholaris.ca:10294/5392