KeenKT: Knowledge Mastery-State Disambiguation for Knowledge Tracing
This addresses the issue of distinguishing true ability from noise in student learning for educational technology, representing an incremental advance with novel method components.
The paper tackled the problem of ambiguity in judging student mastery in knowledge tracing by proposing KeenKT, which uses a Normal-Inverse-Gaussian distribution to model knowledge states and outperformed state-of-the-art models with maximum improvements of 5.85% in AUC and 6.89% in ACC.
Knowledge Tracing (KT) aims to dynamically model a student's mastery of knowledge concepts based on their historical learning interactions. Most current methods rely on single-point estimates, which cannot distinguish true ability from outburst or carelessness, creating ambiguity in judging mastery. To address this issue, we propose a Knowledge Mastery-State Disambiguation for Knowledge Tracing model (KeenKT), which represents a student's knowledge state at each interaction using a Normal-Inverse-Gaussian (NIG) distribution, thereby capturing the fluctuations in student learning behaviors. Furthermore, we design an NIG-distance-based attention mechanism to model the dynamic evolution of the knowledge state. In addition, we introduce a diffusion-based denoising reconstruction loss and a distributional contrastive learning loss to enhance the model's robustness. Extensive experiments on six public datasets demonstrate that KeenKT outperforms SOTA KT models in terms of prediction accuracy and sensitivity to behavioral fluctuations. The proposed method yields the maximum AUC improvement of 5.85% and the maximum ACC improvement of 6.89%.