Review of Knowledge Tracing Model for Intelligent Education

Abstract

As one of the key research directions in the field of intelligent education, knowledge tracing (KT) makes use of a large amount of learning trajectory information provided by the intelligent tutoring system (ITS) to model students, measure their knowledge level automatically, and provide personalized learning programs for them, to achieve the purpose of AI-assisted education. The research progress of knowledge tracing models for intelligent education is reviewed comprehensively. Three representative models are knowledge tracing based on Bayes, knowledge tracing based on Logistic regression model, and deep learning knowledge tracing which has developed rapidly in recent years and shows better performance. Knowledge tracing based on Bayes is divided into Bayesian knowledge tracing (BKT) and BKT model combining personalization, knowledge correlation, node state and real problem expansion. Knowledge tracing based on Logistic regression model is divided into item response theory (IRT) and factor analysis model. Knowledge tracing based on deep learning can be divided into deep knowledge tracing (DTK) and its improved model, designing network structure and introducing attention mechanism. The international open education datasets available to researchers and the commonly used model evaluation indicators are introduced. The performance, characteristics and application scenarios of different types of methods are compared and analyzed. It also discusses the existing problems of the current research and looks forward to future develop-ment direction.

Keywords

• |knowledge tracing (kt)|intelligent education|bayesian network|logistic regression|deep learning