Using Data Mining Findings To Aid Searching For Better Skill Models

Abstract

One key component of creating an intelligent tutoring system is forming a model that monitors student behavior. Researchers in machine learning area have been using automatic/semi-automatic techniques to search for skill models. One of the semi-automatic approach is learning factor analysis (LFA, Cen, Koedinger & Junker, 2006), which involves human making hypothesis and identifying difficulty factors in the related items. In this paper, we propose a hybrid approach in which we leverage findings from our previous educational data mining work to aid the search for a better skill model and thus, improve the efficiency of LFA. Preliminary results suggest that our approach can lead to significantly better fitted skill models fast.

Keywords: Data mining, transfer model, learning factor analysis.