Integrating Semi-Supervised Learning And Ensemble Deep Learning For Low-Resource Deep Knowledge Tracing

Author

Uchechukwu Melody Okechukwu, Prairie View A&M University

Date of Award

12-2025

Document Type

Thesis

Degree Name

Master of Science

Department

Computer Science

Abstract

As learning platforms scale, two obstacles prevent Deep Knowledge Tracing (DKT) from thriving in practice: the scarcity of labeled interactions and the opacity of predictions. We introduced a semi-supervised, ensemble DKT pipeline that trains diverse architectures, including Knowledge Proficiency Tracing (KPT), Exercise-Correlated KPT (EKPT), and Dynamic Key-Value Memory Networks (DKVMN) on a mixture of limited labeled and abundant unlabeled learner interactions, then aggregates predictions via majority voting to stabilize learning and reduce variance. Evaluated on benchmark datasets such as ASSISTments, the combined approach yields consistent gains in AUC, accuracy, and precision over strong supervised baselines while revealing influential interactions, surfacing spurious correlations and temporal leakage risks, and guiding targeted interventions. This contribution provides data-efficient pipelines that enhance predictive performance, foster educator trust, and support personalized learning at scale.

Index Terms — Education data mining, knowledge tracing, machine learning, MOOC.

Committee Chair/Advisor

Lin Li

Committee Co-Chair

Xishuang Dong

Committee Member

Md Hossain Shuvo

Committee Member

Lening Wang

Rights

Date of Digitization

01/12/2026

Contributing Institution

J. B . Coleman Library

City of Publication

Prairie View

MIME Type

Application/PDF

Recommended Citation

Okechukwu, U. (2025). Integrating Semi-Supervised Learning And Ensemble Deep Learning For Low-Resource Deep Knowledge Tracing. Retrieved from https://digitalcommons.pvamu.edu/pvamu-theses/1662