Electronic Theses and Dissertations Archive

Date

2026

Document Type

Thesis

Degree Name

Master of Science

Department

Psychology

Committee Chair

Shelbi Kuhlmann

Committee Member

Andrew Tawfik

Committee Member

Gina Caucci

Abstract

The present study examined whether static personalization strategies can reduce dropout in short-duration online data science learning. Using a 2 × 2 factorial design, 98 undergraduate participants completed an online learning activity that either (a) aligned instructional materials with their learning preference (sequential vs. global) or (b) included a personalized non-interactive pedagogical agent. Retention was operationalized dichotomously (completion vs. dropout). Logistic regression analyses indicated that learning preference personalization significantly increased the odds of completion, whereas the pedagogical agent alone did not show a reliable main effect. However, the interaction between learning preference personalization and agent presence was statistically significant, suggesting that the benefits of preference-aligned materials depended on whether the agent was present. Additional exploratory models examined the role of prior knowledge (pretest scores), prior experience in statistics, programming, and data science, and computational thinking ability. Higher prior knowledge, programming experience, and computational-thinking scores independently predicted greater odds of completion. Overall, these findings suggest that retention in short online data science courses may be supported by aligning instruction with learners’ preferred approaches while also recognizing the importance of learners’ prior preparation and cognitive skills. Although personalization improved completion rates overall, learners with lower prior knowledge and weaker computational-thinking skills were more likely to disengage from the course. These results suggest that personalization strategies alone may not be sufficient for all learners and may need to be complemented by additional scaffolding and motivational support to better support novice learners in short online educational environments.

Comments

Data is provided by the student.”

Library Comment

Dissertation or thesis originally submitted to ProQuest/Clarivate.

Notes

Open Access

Download

Share

COinS
 

Archival Statement

This item was created or digitized prior to April 24, 2027, or is a reproduction of legacy media created before that date. It is preserved in its original, unmodified state specifically for research, reference, or historical recordkeeping. This material is part of a digital archival collection and is not utilized for current University instruction, programs, or active public communication. In accordance with the ADA Title II Final Rule, the University Libraries provides accessible versions of archival materials upon request. To request an accommodation for this item, please submit an accessibility request form.