English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Intelligent Tutoring Systems have become critically important in futurelearning environments. Knowledge Tracing (KT) is a crucial part of that system.It is about inferring the skill mastery of students and predicting theirperformance to adjust the curriculum accordingly. Deep Learning-based KT modelshave shown significant predictive performance compared with traditional models.However, it is difficult to extract psychologically meaningful explanationsfrom the tens of thousands of parameters in neural networks, that would relateto cognitive theory. There are several ways to achieve high accuracy in studentperformance prediction but diagnostic and prognostic reasoning is more criticalin learning sciences. Since KT problem has few observable features (problem IDand student's correctness at each practice), we extract meaningful latentfeatures from students' response data by using machine learning and data miningtechniques. In this work, we present Interpretable Knowledge Tracing (IKT), asimple model that relies on three meaningful latent features: individual skillmastery, ability profile (learning transfer across skills), and problemdifficulty. IKT's prediction of future student performance is made using aTree-Augmented Naive Bayes Classifier (TAN), therefore its predictions areeasier to explain than deep learning-based student models. IKT also showsbetter student performance prediction than deep learning-based student modelswithout requiring a huge amount of parameters. We conduct ablation studies oneach feature to examine their contribution to student performance prediction.Thus, IKT has great potential for providing adaptive and personalizedinstructions with causal reasoning in real-world educational systems.

Interpretable Knowledge Tracing: Simple and Efficient Student Modeling with Causal Relations