Predicting High-level Student Responses Using Conceptual Clustering

Authors:
Roberto Legaspi;Raymund Sison;Ken-ichi Fukui;Masayuki Numao
Affiliations:
The Institute of Scientific and Industrial Research, Osaka University, Japan, roberto@ai.sanken.osaka-u.ac.jp;College of Computer Studies, De La Salle University-Manila, Philippines;The Institute of Scientific and Industrial Research, Osaka University, Japan, roberto@ai.sanken.osaka-u.ac.jp;The Institute of Scientific and Industrial Research, Osaka University, Japan, roberto@ai.sanken.osaka-u.ac.jp
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 6
Cited 1

C4.5: programs for machine learning

C4.5: programs for machine learning
Self-Organizing Maps

Self-Organizing Maps
Growth and maturity of intelligent tutoring systems: a status report

Smart machines in education
ADVISOR: A Machine Learning Architecture for Intelligent Tutor Construction

Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence
High-Level Student Modeling with Machine Learning

ITS '00 Proceedings of the 5th International Conference on Intelligent Tutoring Systems
A Framework for the Initialization of Student Models in Web-based Intelligent Tutoring Systems

User Modeling and User-Adapted Interaction

Cluster-based predictive modeling to improve pedagogic reasoning

Computers in Human Behavior

Quantified Score

Hi-index	0.00

Visualization

Abstract

A conceptual clustering algorithm can search through huge amounts of data looking for multi-dimensional structures, where each structure or cluster represents a relevant concept in the problem-solving domain. We investigated on the effect of cluster knowledge for a learning agent to improve its prediction of higher level student response aspects. Our empirical results show that when cluster knowledge is utilized by a function approximator, prediction is improved as compared to treating the entire data population as a single cluster.