Knowledge Tracing’s is the de-facto standard for inferring student knowledge from performance data, which uses a simple dynamic Bayesian network (HMM) where the observable variable represents student performance (correct or incorrect) and the hidden variable represents student knowledge state (known or unknown). Unfortunately, it does not allow to model the feature-rich data that is now possible to collect in modern digital learning environments. Because of this, many ad hoc Knowledge Tracing variants have been proposed to model a specific feature of interest. For example, variants have studied the effect of students’ individual characteristics, the effect of help in a tutor, and subskills. These ad hoc models are successful for their own specific purpose, but are specified to only model a single specific feature.
We present FAST (Feature Aware Student knowledge Trac- ing), an efficient, novel method using unsupervised learning with features that allows integrating general features into Knowledge Tracing. We demonstrate FAST’s flexibility with three examples of feature sets that are relevant to a wide audience. We use features in FAST to model (i) multiple subskill tracing, (ii) a temporal Item Response Model implementation, and (iii) expert knowledge. We present empirical results using data collected from an Intelligent Tutoring System. We report that using features can improve up to 25% in classification performance of the task of predicting student performance. Moreover, for fitting and inferencing, FAST can be 300 times faster than models created in BNT-SM, a toolkit that facilitates the creation of ad hoc Knowledge Tracing variants.