TY - GEN
T1 - An intelligent agent that learns how to tutor students
T2 - 13th International Conference on Computers in Education, ICCE 2005
AU - Soh, Leen Kiat
AU - Blank, Todd
PY - 2005
Y1 - 2005
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=84856951070&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84856951070&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84856951070
SN - 9810540051
SN - 9789810540050
T3 - Proc. Int. Conf. on Computers in Education 2005: "Towards Sustainable and Scalable Educational Innovations Informed by the Learning Sciences"- Sharing Research Results and Exemplary Innovations, ICCE
SP - 418
EP - 425
BT - Proc. Int. Conf. on Computers in Education 2005
Y2 - 28 November 2005 through 2 December 2005
ER -