Development and evaluation of an adaptive Web-based intelligent tutoring system
Jens O. Liegle, Kent State University, United States
Kent State University . Awarded
Defined very broadly, adaptive web-based intelligent tutoring systems (ITS) are web-based applications that use the knowledge about the domain, the student, and teaching strategies to support flexible individualized learning and tutoring. Adaptive ITS use knowledge about the primary learning style Of the user to adapt the teaching strategy accordingly. Such systems are seen by many as a potential solution to the ineffectiveness and inefficiency of conventional computer-based training systems.
This dissertation is a compilation of three areas of research regarding the implications of adaptive web-based ITS on the domain programming knowledge.
First, a classification of programming knowledge is presented. Knowledge is classified into declarative and procedural knowledge at different levels of knowledge depth. Teaching strategies and teaching methods in the area of computer programming are identified and matched to the classification of programming knowledge types. The combination of the programming-knowledge classification with the teaching strategies allows instructors and designers of ITS to create a complete curriculum for a programming course.
Second, based on the programming knowledge classification and the various strategies and methods for teaching computer programming, a prototype of a web-based adaptive ITS is developed. The application's functionality is described, including the techniques that were used to integrate an expert system shell into the prototype. Results from a pilot test and an experiment show the effectiveness and limitations of the system.
Third, results from an experiment where a total of four different versions of the prototype were given to the users based on their primary learning style, as measured by a version of Kolb's Learning Style Inventory, are presented. The explorer vs. observer and concrete vs. abstract personality-type dimensions were given a curriculum sequence based on learner- vs. system-control and a presentation sequence that taught the syntax of a new command either before or after the lecture. The results from this experiment and their potential implications for teaching strategies are discussed.
The results of this research may be applied to a wide range of topics, including, but not limited to, adaptive web-based intelligent tutoring systems, programming knowledge classifications, cognitive psychology, and curriculum and presentation sequencing.
Liegle, J.O. Development and evaluation of an adaptive Web-based intelligent tutoring system. Ph.D. thesis, Kent State University.
Citation reproduced with permission of ProQuest LLC.
For copies of dissertations and theses: (800) 521-0600/(734) 761-4700 or https://dissexpress.umi.com