Modeling Student Performance Using Feature Crosses Information for Knowledge Tracing

Abstract

Knowledge tracing (KT) is an intelligent educational technology used to model students' learning progress and mastery in adaptive learning environments for personalized education. Despite utilizing deep learning models in KT, current approaches often oversimplify students' exercise records into knowledge sequences, which fail to explore the rich information within individual questions. In addition, existing KT models tend to neglect the complex, higher order relationships between questions and latent concepts. Therefore, we introduce a novel model called feature crosses information-based KT (FCIKT) to explore the intricate interplay between questions, latent concepts, and question difficulties. FCIKT utilizes a fusion module to perform feature crosses operations on questions, integrating information from our constructed multirelational heterogeneous graph using graph convolutional networks. We deployed a multihead attention mechanism, which enriches the static embedding representations of questions and concepts with dynamic semantic information to simulate real-world scenarios of problem-solving. We also used gated recurrent units to dynamically capture and update the students' knowledge state for final prediction. Extensive experiments demonstrated the validity and interpretability of our proposed model.