Date of Award

5-2025

Document Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

Degree Discipline

Electrical Engineering

Abstract

In today’s educational landscape, the demand for personalized learning experiences has gained significant attention, driven by advances in Artificial Intelligence (AI) and deep learning technologies. This dissertation investigated the integration of Generative Artificial Intelligence (GAI) with Deep Knowledge Tracing (DKT) to advance Personalized Adaptive Learning (PAL) systems, particularly within Historically Black Colleges and Universities (HBCUs). While HBCUs play a pivotal role in expanding educational opportunities, they often face challenges such as lower retention and graduation rates.

This research began by exploring the theoretical foundations of personalized learning and DKT, a data-driven technique that models learner knowledge acquisition over time. Using four years of educational data from Fall 2019 to Summer 2023 from Prairie View A&M University (PVAMU), this study aimed to enhance STEM education by predicting student course outcomes and identifying at-risk students. Multiple state-of-the-art (SOTA) DKT models, including DKT, DKT+, DKVMN, SAKT, and KQN, were employed to evaluate knowledge tracing performance. Results revealed that SAKT and KQN consistently achieved superior predictive accuracy, AUC, and F1 scores, enabling faculty and advisors to proactively support students through timely interventions.

A key advancement of this study was addressing the challenge of data scarcity, which often limits DKT effectiveness in resource-constrained environments like HBCUs. To overcome this, GAI models such as TABSYN, TabDDPM, and GReaT were used to generate synthetic datasets that augmented real student records. The integration of tabular GAI enhanced the robustness of DKT models, resulting in improved prediction accuracy and expanding the applicability of PAL systems across diverse educational contexts.

In conclusion, this dissertation advances the field of DKT by integrating innovative approaches that enhance PAL systems at HBCUs. It demonstrated how combining DKT with GAI for synthetic data augmentation can improve educational outcomes. Moreover, it highlighted the importance of collaboration between AI researchers and educators to develop data-driven techniques that support students through improved resource allocation, timely interventions, and refined support strategies.

Index Terms: deep knowledge tracing, educational data mining, generative artificial intelligence, historically Black colleges and universities, personalized adaptive learning, synthetic data generation.

Committee Chair/Advisor

Xiangfang Li

Committee Member

Lijun Qian

Committee Member

Xishuang Dong

Committee Member

Pamela Obiomon

Committee Member

Nicholas Duffield

Publisher

Prairie View A&M University

Rights

© 2021 Prairie View A & M University

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Date of Digitization

5-30-2025

Contributing Institution

John B Coleman Library

City of Publication

Prairie View

MIME Type

Application/PDF

Download


Share

COinS