Keywords

Affective Computing, Emotion Regulation, Education, Learning, Facial Expression Recognition

Abstract

This publication-based dissertation examined the empirical value and ethical implications of affective computing in educational contexts, focusing on facial expression recognition as an exemplary affective data stream. This dissertation includes three studies designed to explore the methodological contributions and ethical concerns tied to the use of affective computing in education contexts. The first empirical study analyzed trace data from students’ online self-regulated learning (SRL) behaviors using clustering and process mining techniques to model changes in goals and learning processes. While this study used multichannel data to examine dynamic SRL strategies, the absence of affective data limited researchers’ ability to understand the why behind learner behaviors. In contrast, the second empirical study analyzed affective data, utilizing multilevel modeling to examine if dynamic instructor expressions can be used to capture teacher emotion regulation processes across live instruction. The results of this study highlight the methodological advancements possible with emerging affective data channels like facial expression recognition as well as the inherent limitations present outside of controlled research settings. The third study provides an in-depth ethical analysis on the use of affective computing tools in classroom settings. This analysis weighs the empirical benefits of affective data against the risks of applying these tools in real-world educational settings. Findings from these studies are used to argue that while affective data channels like facial expression recognition can enhance the granularity and temporal precision of research on the role of emotions in teaching and learning, there are considerable ethical concerns that make the application of certain affective recognition technologies inappropriate for real-world educational settings. This dissertation concludes with recommendations for future research and proposed guardrails for the use of affective computing in learning and teaching.

Completion Date

2026

Semester

Spring

Committee Chair

Dr. Michelle Taub

Degree

Doctor of Philosophy (Ph.D.)

College

College of Community Innovation and Education

Department

Learning Sciences and Educational Research

Format

PDF

Document Type

Thesis

Identifier

DP0053302

Release Date

5-15-2027

Download

Available for download on Saturday, May 15, 2027

Share

COinS
 

Accessibility 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. 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.