DKT-STDRL: Spatial and Temporal Representation Learning Enhanced Deep Knowledge Tracing for Learning Performance Prediction

TL;DR

This paper introduces DKT-STDRL, a novel deep learning model that combines CNN and BiLSTM to extract spatial and temporal features from student learning sequences, significantly improving performance in predicting learning outcomes.

Contribution

The paper proposes a new deep knowledge tracing model that integrates spatial and temporal feature extraction, enhancing learning performance prediction accuracy over existing models.

Findings

Outperforms DKT and CKT on multiple datasets

Effectively captures complex learning features

Improves prediction accuracy in educational datasets

Abstract

Knowledge tracing (KT) serves as a primary part of intelligent education systems. Most current KTs either rely on expert judgments or only exploit a single network structure, which affects the full expression of learning features. To adequately mine features of students' learning process, Deep Knowledge Tracing Based on Spatial and Temporal Deep Representation Learning for Learning Performance Prediction (DKT-STDRL) is proposed in this paper. DKT-STDRL extracts spatial features from students' learning history sequence, and then further extracts temporal features to extract deeper hidden information. Specifically, firstly, the DKT-STDRL model uses CNN to extract the spatial feature information of students' exercise sequences. Then, the spatial features are connected with the original students' exercise features as joint learning features. Then, the joint features are input into the BiLSTM part. Finally, the BiLSTM part extracts the temporal features from the joint learning features to obtain the prediction information of whether the students answer correctly at the next time step. Experiments on the public education datasets ASSISTment2009, ASSISTment2015, Synthetic-5, ASSISTchall, and Statics2011 prove that DKT-STDRL can achieve better prediction effects than DKT and CKT.