AI Insight
This study investigates how Knowledge Tracing models in Intelligent Tutoring Systems can maintain accuracy when encountering new questions with no prior student interaction data. The researchers developed PICKT (Practical Integrated Cross-consistent Knowledge Tracing) and tested which features help models handle this "cold start" problem. They found that difficulty ratings were most useful for very challenging questions, while text-based and knowledge map features enabled models to infer properties of new questions by comparing them to similar previously-seen questions.
Why it matters
These findings can improve the reliability of adaptive learning systems when introducing new content, ensuring students continue to receive accurate assessments and personalized learning recommendations even as question banks are updated or expanded.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
Abstract: Intelligent Tutoring Systems (ITS) provide personalized learning paths by diagnosing learners’ proficiency. Knowledge Tracing (KT) models play a central role in this diagnosis by estimating learners’ evolving knowledge states. However, in real-world ITS services, diagnostic reliability may decrease when newly introduced questions have no prior interaction history. This study aims to empirically identify the key features that support KT model robustness under the question cold start situation. To this end, we designed Practical Integrated Cross-consistent Knowledge Tracing (PICKT), which integrates multiple types of features, and examined which feature contributes to robustness under the question cold start situation. Among these features, we further analyzed difficulty, texts, and relational information derived from the knowledge map, which have been identified as important factors in prior KT research, to examine how each contributes to robustness under the question cold start situation. The results showed that difficulty feature was particularly informative for highly challenging questions, where the likelihood of a correct response rate was remarkably low. Meanwhile, the fused texts and knowledge map features supported robustness by enabling the model to estimate the representation of unseen questions by leveraging semantically and structurally similar questions observed during training. These findings suggest that maintaining KT robustness in ITS applications requires prioritization of feature annotation aligned with the characteristics of educational services.
Source: Enhancing knowledge tracing robustness for new question cold start in Intelligent Tutoring Systems