Paper Authors

Abstract

NOTE: The first page of text has been automatically extracted and included below in lieu of an abstract

Session 2520

Applying Multiple Student Modeling Techniques In Intelligent Tutoring Systems Essam M. Kosba, Ahmed R. Dawoud Arab Academy for Science & Technology / October University For Modern Sciences

Abstract

An important aspect of Intelligent Tutoring Systems (ITSs) is their ability to provide individualized instruction in a manner similar to what offered by a personal human instructor. A student model is described as the information that ITS keeps about an individual student. ITSs should actively support the student’s learning process through tailoring the teaching process carried out to each individual student. The main purpose of a student model is to provide the planning component of an ITS with the information it needs to select a suitable instructional action. Probability Theory Intelligent Tutoring System (PTITS) is an intelligent system for teaching the fundamentals of the probability theory. The PTITS’ approach to building the student model relies on gathering a great deal of information about the student through employment of both overlay and buggy models. An approach to inexact modeling of student ability based on certainty theory and fuzzy sets theory was adopted as a way to formulate the knowledge required in these models. More adaptability to the student status and more flexibility to diagnose student misconceptions are the main goals behind the conjunction of both models in PTITS. The developed architecture opens the door for more participation from teachers and instructors in developing their own courses using ITSs and hence for more conviction with ITSs’ role in education.

1- Introduction

It is known that the development of any applied ITS is an extremely difficult and complex problem. This is because most of the developers start their ITSs from scratch, and therefore they have to build all of its complex parts, which take great effort and long time. In general, applied ITSs are developed on the basis of preliminary elaborated Expert Systems (ES) in the domain under study. These ES model the processes of problem solving in certain domain by an expert and thus represent Expert Models. Then student model is build upon ES. Finally, the pedagogical functions or Tutor Model is developed.

The main goal of this research is to build up an ITS that use both overlay and buggy student modeling approaches. Probability theory, as an important course in pre-engineering curricula, was adopted to present a domain for applying ideas of this research. The resulted system is called “Probability Theory Intelligent Tutoring System” or PTITS. The Knowledge base for probability theory and its problem solver are not available. So, a major technical consideration of our work is to lessen the complexity of the knowledge acquisition process and software engineering requirements involved in building of the domain knowledge base and problem solver without affecting our work in PTITS’ student model. It is important to note that, when we simplify the knowledge engineering processes this will lead to more

• Citation

• Format
  • APA
  • APA - LaTeX bibitem
  • MLA
  • MLA - LaTeX bibitem
  • Bibtex
  • EndNote - RIS

Kosba, E. M., & Dawoud, A. (1999, June), Applying Multiple Student Modeling Techniques In Intelligent Tutoring Systems Paper presented at 1999 Annual Conference, Charlotte, North Carolina. 10.18260/1-2--7652