Integrating LSTM and BERT for Long-Sequence Data Analysis in Intelligent Tutoring Systems

This paper proposes LBKT, a hybrid LSTM-BERT model for Knowledge Tracing in Intelligent Tutoring Systems that predicts student performance on subsequent learning tasks by analyzing long-sequence interaction data. The model is evaluated on multiple benchmark datasets (including EdNet and Junyi Academy) using accuracy and AUC metrics, with ablation studies and t-SNE visualizations to demonstrate interpretability.

The field of Knowledge Tracing aims to understand how students learn and master knowledge over time by analyzing their historical behaviour data. To achieve this goal, many researchers have proposed Knowledge Tracing models that use data from Intelligent Tutoring Systems to predict students' subsequent actions. However, with the development of Intelligent Tutoring Systems, large-scale datasets containing long-sequence data began to emerge. Recent deep learning based Knowledge Tracing models face

Study Type

Source

Framework Categories

Tool Types

Tags