Could not find session

2026 ASEE Annual Conference & Exposition

Integrating Facial Emotion Analysis and Large Language Models to Investigate Student Engagement in Online Engineering Courses

Presented at The Intersection of AI and Methods for Research and Teaching

This research brief explores a multimodal approach to investigating student engagement in fully online, asynchronous engineering courses. The study integrates student self-reported emotions, instructor observations, and AI-assisted facial expression analysis to examine affective and attentional signals that may support a richer understanding of engagement during short problem-solving tasks embedded in online course modules. The proposed method is designed for online asynchronous learning environments, where instructors have limited access to the real-time behavioral cues that often inform support in face-to-face classrooms. To support preliminary development of the AI workflow, this study uses the publicly available DIPSER dataset to examine the extent to which a vision-language model can infer student emotion and attention from cropped facial images and head-pose information. Results suggest that model predictions are more plausible when facial cues are visually clear, but less reliable when expressions are subtle or ambiguous, underscoring the limitations of single-frame analysis. These findings support the feasibility of the proposed approach while motivating future research in online asynchronous engineering courses to examine how triangulated engagement data can inform instructional design and student support.

Authors

Julianna Gesun http://orcid.org/0000-0002-0084-951X Embry-Riddle Aeronautical University [biography]

Julianna Gesun, Ph.D., is currently an assistant professor of engineering whose research broadly focuses on understanding and supporting the process by which engineering programs facilitate the environments for students to develop optimal functioning in undergraduate engineering programs. Her research interests intersect the fields of positive psychology, engineering education, and human development to understand the intrapersonal, cognitive, social, behavioral, contextual, cultural, and outcome factors that influence thriving in engineering.
Lingxiao Wang Louisiana Tech University [biography]

Dr. Lingxiao Wang is an Assistant Professor of Electrical Engineering at Louisiana Tech University. He earned his Ph.D. in Electrical Engineering and Computer Science in 2021 and his M.S. in Electrical and Computer Engineering in 2018, both from Embry-Riddle Aeronautical University. His research interests include robotics, autonomous systems, and artificial intelligence.
Dr. Ghazal Barari http://orcid.org/0000-0002-1047-7617 Embry-Riddle Aeronautical University [biography]

Dr. GHAZAL BARARI is an Associate Professor of Engineering at Embry-Riddle Aeronautical University Worldwide. With a Ph.D. in Mechanical Engineering from the University of Central Florida, her research pivoted from combustion and biofuel’s reaction mechanism to engineering education and student success pathways. She studies AI applications in curriculum design, simulation-based learning, and students’ engagement in online environments. She leads the Engineering Fundamentals program’s ABET accreditation, serves as an editor for International Journal of Aviation, Aeronautics, and Aerospace, and has been recognized for her innovative teaching and service.
Elaina Hudiburg Embry-Riddle Aeronautical University - Daytona Beach
Khan Raqib Mahmud http://orcid.org/https://0000-0002-6473-2978 Louisiana Tech University

Note

The full paper will be available to logged in and registered conference attendees once the conference starts on June 21, 2026, and to all visitors after the conference ends on June 24, 2026

« View session