Leveraging Pedagogical Theories to Understand Student Learning Process with Graph-based Reasonable Knowledge Tracing

This paper proposes GRKT, a graph-based knowledge tracing method that models students' evolving knowledge mastery through a three-stage process (knowledge retrieval, memory strengthening, and learning/forgetting) informed by pedagogical theories. The approach addresses unreasonableness in existing deep learning knowledge tracing models by explicitly modeling knowledge concept relationships and learning dynamics.

Knowledge tracing (KT) is a crucial task in intelligent education, focusing on predicting students' performance on given questions to trace their evolving knowledge. The advancement of deep learning in this field has led to deep-learning knowledge tracing (DLKT) models that prioritize high predictive accuracy. However, many existing DLKT methods overlook the fundamental goal of tracking students' dynamical knowledge mastery. These models do not explicitly model knowledge mastery tracing processe

Study Type

Source

Framework Categories

Tool Types

Tags