Cluster analysis of student activity in a web-based intelligent tutoring system

In this paper we present a model of a system for integration of an intelligent tutoring system with data mining tools. The purpose of the integration is twofold; a) to power the system adaptability based on clustering and sequential pattern mining, and b) to enable teachers (non-experts in data mining) to use data mining techniques in their web browser on a daily basis, and get useful visualizations that provide insights into the learning progress of their students. We also present an approach to clustering results evaluation developed so that the system can independently deduce the best number of clusters for the k-means algorithm as well as order the clusters in terms of learning efficiency of cluster members (students).