Extracting Causal Relations in Deep Knowledge Tracing

This paper investigates the mechanisms behind Deep Knowledge Tracing (DKT) models, demonstrating that their predictive success stems from modeling prerequisite causal relationships between knowledge components rather than bidirectional dependencies, using the Assistments dataset to extract and validate causal exercise relation graphs.

A longstanding goal in computational educational research is to develop explainable knowledge tracing (KT) models. Deep Knowledge Tracing (DKT), which leverages a Recurrent Neural Network (RNN) to predict student knowledge and performance on exercises, has been proposed as a major advancement over traditional KT methods. Several studies suggest that its performance gains stem from its ability to model bidirectional relationships between different knowledge components (KCs) within a course, enabl

Study Type

Source

Framework Categories

Tool Types

Tags