Back to search

North Texas State University

The Use of Learning Theory in the Application of Artificial Intelligence to Computer-Assisted Instruction of Physics

Abstract

dc:description

It was the purpose of this research, to develop and test an artificially intelligent, learner-based, computer-assisted physics tutor. The resulting expert system is named ARPHY, an acronym for ARtificially intelligent PHYsics tutor. The research was conducted in two phases. In the first phase of the research, the system was constructed using Ausubel's advance organizer as a guiding learning theory. The content of accelerated motion was encoded into this organizer after sub-classification according to the learning types identified by Gagnds. The measurement of the student's level of learning was accomplished through the development of questioning strategies based upon Bloom's taxonomy of educational objectives. The second phase of this research consisted of the testing of ARPHY. Volunteers from four levels of first-semester physics classes at North Texas State University were instructed that their goal was to solve three complex physics problems related to accelerated motion. The only students initially instructed by ARPHY were from the class of physics majors. When the threshold values of the pedagogical parameters stabilized, indicating the fact that ARPHY's instructional technique had adapted to the class' learning style, students from other classes were tutored. Nine of the ten students correctly solved the three problems after being tutored for an average of 116 minutes. ARPHY's pedagogical parameters stabilized after 6.3 students. The remaining students, each from a different class, were tutored, allowing ARPHY to self-improve, resulting in a new tutorial strategy after each session. It is recommended that future research into intelligent tutoring systems for science incorporate the principles and theories of learning which this research was based upon. An authoring system based upon the control structure of ARPHY should be developed, since the modular design of this system will allow any field which can be organized into a net-archy of problems, principles, and concepts, to be tutored.

Degree

thesis:*
Grantor dc:publisher
North Texas State University
Year dc:date
1985

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Brown, Stephen F. (Stephen Francis)
Contributors dc:contributor
  • Miller, James R.
  • Deering, William D.
  • Kingery, Dwane
  • Swigger, Kathleen M.

Subjects

dc:subject × 5

Rights

dc:rights
Statement dc:rights
  • Public
  • Brown, Stephen F. (Stephen Francis)
  • Copyright
  • Copyright is held by the author, unless otherwise noted. All rights reserved.
Language dc:language
English

Identifiers

dc:identifier.*
Identifier
local-cont-no: 1002779311-Brown
call-no: 379 N81d no. 2361
untcat: b1338619
oclc: 13687039
ark: ark:/67531/metadc330775

Chain of custody

source
Harvested from
University of North Texas
Base URL
digital.library.unt.edu/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Brown, Stephen F. (Stephen Francis). The Use of Learning Theory in the Application of Artificial Intelligence to Computer-Assisted Instruction of Physics. North Texas State University, 1985. https://digital.library.unt.edu/ark:/67531/metadc330775/