Incorporating Rich Features into Deep Knowledge Tracing

The desire to follow student learning within intelligent tutoring systems in near real time has led to the development of several models anticipating the correctness of the next item as students work through an assignment. Such models have included Bayesian Knowledge Tracing (BKT), Performance Factors Analysis (PFA), and more recently with developments in deep learning, Deep Knowledge Tracing (DKT). This DKT model, based on the use of a recurrent neural network, exhibited promising results. Thus far, however, the model has only considered the knowledge components of the problems and correctness as input, neglecting the breadth of other features collected by computer-based learning platforms. This work seeks to improve upon the DKT model by incorporating more features at the problem-level. With this higher dimensional input, an adaption to the original DKT model structure is also proposed, incorporating an auto-encoder network layer to convert the input into a low dimensional feature vector to reduce both the resource requirement and time needed to train. Experiment results show that our adapted DKT model, observing more combinations of features, can effectively improve accuracy.