A Face-to-Face Education Support System Capable of Lecture Adaptation and Q&A Assistance Based On Probabilistic Inference

Keys to high-quality face-to-face education are ensuring flexibility in the way lectures are given, and providing care and responsiveness to learners. This paper describes a face-to-face education support system that is designed to raise the satisfaction of learners and reduce the workload on instructors. This system consists of a lecture adaptation assistance part, which assists instructors in adapting teaching content and strategy, and a Q&A assistance part, which provides learners with answers to their questions. The core component of the former part is a “learning achievement map", which is composed of a Bayesian network (BN). From learners- performance in exercises on relevant past lectures, the lecture adaptation assistance part obtains information required to adapt appropriately the presentation of the next lecture. The core component of the Q&A assistance part is a case base, which accumulates cases consisting of questions expected from learners and answers to them. The Q&A assistance part is a case-based search system equipped with a search index which performs probabilistic inference. A prototype face-to-face education support system has been built, which is intended for the teaching of Java programming, and this approach was evaluated using this system. The expected degree of understanding of each learner for a future lecture was derived from his or her performance in exercises on past lectures, and this expected degree of understanding was used to select one of three adaptation levels. A model for determining the adaptation level most suitable for the individual learner has been identified. An experimental case base was built to examine the search performance of the Q&A assistance part, and it was found that the rate of successfully finding an appropriate case was 56%.

• Yoshitaka Fujiwara
• Jun-ichirou Fukushima
• Yasunari Maeda

• Bayesian network
• face-to-face education
• lecture adaptation
• Q&A assistance.

[1] E. M. Cashman and E. A. Eschenbach, Active Learning with Web
Technology-Just In Time!, 33rd ASEE / IEEE Frontiers in Education
Conference, Boulder, U.S.A., pp.T3F-9-T3F-13, 2003.
[2] S. Eom, The Role of the Instructors as a Determination of Students-
Satisfaction in University Online Education, Proceedings of the Sixth
International Conference on Advanced Learning Technologies, Kerkrade,
Netherlands, pp.985-988, 2006.
[3] F. V. Jensen, Bayesian Networks and Decision Graphs, Springer-Verlag,
2001.
[4] Y. Fujiwara, Y. Ohnishi, H. Yoshida, A Method for Tuning the Structure
of a Hierarchical Causal Network Used to Evaluate a Learner-s Profile,
IEICE Trans. Inf. & Syst., Vol.E89-D, No.7, pp.2310-2314, 2006.
[5] Y. Fujiwara, H. Yoshida, Y. Maeda, S. Okada, T. Suzuki, Ubiquitous
Learning System Featuring User-adaptive Teaching Strategy,
Proceedings of the IADIS International Conference CELDA 2006,
Barcelona, Spain, pp.243-250, 2006.
[6] Y. Fujiwara, S. Okada, T. Suzuki, Y. Ohnishi, H. Yoshida, Self-Adaptive
Java Production System and Its Application to a Learning Assistance
System, IEICE Trans. Inf. & Syst., Vol.E87-D, No.9,pp.2186-2194,
2004.
[7] Y. Fujiwara, S. Abe, Y. Maeda, Help Desk Architecture for a U-learning
System Characterized by the Use of Probabilistic Reasoning-based Search
of a Case Base, Proceedings of the 7th IASTED International Conference
on Web-based Education(WBE 2008), Innsbruck, Austria, pp.57-62,
2008.
[8] T. L. Acorn, S. H. Walden, SMART: Support Management Cultivated
Reasoning Technology for Compaq Customer Service, In Innovative
Applications of Artificial Intelligence 4, 10th National Conf. on Artificial
Intelligence, San Jose, USA, 1992.
[9] I. Watson, A. Basden, P. S. Brandon, A Client Centered Approach to the
Development of Expert Systems, Expert Systems, 9(4), 1992, 181-188.
[10] J. Boron, D. Morales, P. Klah, Developing and Deploying Knowledge on
a Global Scale, In Innovative Applications of Artificial Intelligence 5,
13th National Conf. on Artificial Intelligence, Portland, USA,1996.
[11] Y. Kiyota, S. Kurohashi, and F. Kido, Dialog Navigator: A Question
Answering System based on Large Text Knowledge Base, Natural
Language Processing, 10(4), 2003, 1-30.
[12] Y. Matsumoto, Morphologic Analysis System Chasen, IPSJ Magazine,
41(11), 2000, 1208-1214.
[13] T. Kudoh, Y. Matsumoto, Japanese Dependency Structure Analysis based
on Support Vector Machine, IPSJ SIG Notes, 2000-NL-138-11, 2000,
79-86.