An Intelligent Agent that Learns How to Tutor Students: Design and Results

Authors:
Leen-Kiat Soh;Todd Blank
Affiliations:
Department of Computer Science and Engineering, University of Nebraska, Lincoln, NE 68588-0115 USA, {lksoh, tblank}@cse.unl.edu;Department of Computer Science and Engineering, University of Nebraska, Lincoln, NE 68588-0115 USA, {lksoh, tblank}@cse.unl.edu
Venue:
Proceedings of the 2005 conference on Towards Sustainable and Scalable Educational Innovations Informed by the Learning Sciences: Sharing Good Practices of Research, Experimentation and Innovation
Year:
2005

Citing 5
Cited 2

Case-based reasoning

Case-based reasoning
Intelligent tutoring systems with conversational dialogue

AI Magazine
Growth and maturity of intelligent tutoring systems: a status report

Smart machines in education
Shared reality: physical collaboration with a virtual peer

CHI '00 Extended Abstracts on Human Factors in Computing Systems
Andes: A Coached Problem Solving Environment for Physics

ITS '00 Proceedings of the 5th International Conference on Intelligent Tutoring Systems

Integrating Case-Based Reasoning and Meta-Learning for a Self-Improving Intelligent Tutoring System

International Journal of Artificial Intelligence in Education
Integrated introspective case-based reasoning for intelligent tutoring systems

AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 2

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we describe an intelligent agent that presents different learning content such as tutorials, examples, and problems adaptively to individual students and learns from its interaction with the students how to improve its performance. We have built an end-to-end intelligent tutoring system, premised on the above goal, with a graphical user interface (GUI) front-end, an agent powered by case-based reasoning (CBR), and a mySQL database backend. We use a casebase to store the pedagogical strategies, embedded in the individual cases and the similarity retrieval and adaptation heuristics. Each case has situation, solution and outcome parameters. The situation parameters include the students' static and dynamic profiles and the instructional content's characteristics while the solution parameters specify the characteristics of the example or problem to be delivered to the student. We developed a set of CS1 content that includes five topics and deployed our system in the laboratories. Our results show that when the machine learning mechanism is activated, our agent is able to learn to tutor students more efficiently.