SAINT+: Integrating Temporal Features for EdNet Correctness Prediction
This work addresses knowledge tracing for educational applications, but it is incremental as it builds directly on an existing model with minor enhancements.
The authors tackled the problem of predicting student correctness in knowledge tracing by integrating temporal features into a Transformer-based model, resulting in a 1.25% improvement in AUC on the EdNet dataset compared to the previous state-of-the-art.
We propose SAINT+, a successor of SAINT which is a Transformer based knowledge tracing model that separately processes exercise information and student response information. Following the architecture of SAINT, SAINT+ has an encoder-decoder structure where the encoder applies self-attention layers to a stream of exercise embeddings, and the decoder alternately applies self-attention layers and encoder-decoder attention layers to streams of response embeddings and encoder output. Moreover, SAINT+ incorporates two temporal feature embeddings into the response embeddings: elapsed time, the time taken for a student to answer, and lag time, the time interval between adjacent learning activities. We empirically evaluate the effectiveness of SAINT+ on EdNet, the largest publicly available benchmark dataset in the education domain. Experimental results show that SAINT+ achieves state-of-the-art performance in knowledge tracing with an improvement of 1.25% in area under receiver operating characteristic curve compared to SAINT, the current state-of-the-art model in EdNet dataset.