2026 ASEE Annual Conference & Exposition

Generative AI as a Reflection Partner in Quantitative Engineering Education: A Pilot Implementation in a Construction Equipment Course

Presented at CONST 2 - Generative AI and ChatGPT: New Partners in Construction Learning

Complex calculations such as earth volume estimation and equipment productivity analysis (e.g., shovel or excavator cycles) often challenge construction management students because they require multiple steps, interrelated parameters, and a solid grasp of quantitative reasoning. This study investigates the potential of generative AI tools (such as Copilot) as a “reflection partner” to help students articulate their reasoning process and strengthen their ability to evaluate their own problem-solving approaches. The pilot was conducted in a Construction Equipment course with 33 enrolled undergraduate students, where students first completed two problem sets—one focusing on earthwork volume and another on equipment productivity—without AI assistance. Afterward, they engaged the AI by sharing their step-by-step reasoning and asking for diagnostic feedback on possible errors, overlooked assumptions, or suggested improvements. Students then revised their work and completed a short, open-ended reflection survey designed to capture their experiences, perceptions, and self-reported learning processes when using AI as a reflection partner.

Preliminary results indicate that AI-supported reflection encouraged students to think more deliberately about their calculation logic, uncover hidden misconceptions, and focus on understanding rather than merely arriving at the right number. Students also reported a stronger sense of confidence and awareness of how they learn best. While demonstrated in a construction context and based on a single-course pilot, this approach shows promise for integrating generative AI reflection activities into other STEM courses that emphasize problem solving and quantitative analysis. It offers a practical and low-cost framework for instructors seeking new ways to use AI to foster metacognitive growth and more reflective learning.

Authors

Dr. Tianjiao Zhao http://orcid.org/0000-0002-1897-3797 East Carolina University [biography]

Dr. Tianjiao Zhao is an Assistant Professor in the Department of Construction Management at East Carolina University, USA. Her research focuses on integrating artificial intelligence, visualization, and human–computer interaction to improve efficiency, safety, and sustainability in construction management. She is also committed to incorporating emerging technologies into construction education to support data-driven decision-making and workforce development.
Dr. Ri Na University of Delaware [biography]

Ri Na is an Associate Professor in the Department of Civil, Construction, and Environmental Engineering at the University of Delaware. Her teaching and research focus on construction education, digital technologies, and improving student learning through tools such as BIM, AR/VR, and 3D printing.
Xi Lin East Carolina University [biography]

Dr. Xi Lin is an associate professor at East Carolina University, US. Her research focuses on seeking best practices to enhance student engagement and interaction in online learning environments. More information can be found at http://whoisxilin.weebly.com/
Dr. Xi Wang Drexel University [biography]

Dr. Xi Wang is an Associate Teaching Professor at Drexel University. She received her Ph.D. and M.Eng both in Civil Engineering, from the University of Kentucky and Auburn University. She is licensed as a Professional Engineer and LEED Green Associate. She is teaching a range of courses in construction management and will be assisting capstone design projects that directly serve regional construction firms. Her research interests include technology adoption in workforce development in the construction industry, sustainable developments in construction education, and learning motivation for student success in engineering education.
Chen Xia Western New England 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

For those interested in:

Faculty