Generative AI as a Reflective Scaffold in a UAV-Based STEM Project: A Mixed-Methods Study on Students' Higher-Order Thinking and Cognitive Transformation
Saved in:
| Title: | Generative AI as a Reflective Scaffold in a UAV-Based STEM Project: A Mixed-Methods Study on Students' Higher-Order Thinking and Cognitive Transformation |
|---|---|
| Language: | English |
| Authors: | Shih-Yeh Chen, Wei-Cheng Chen, Chin-Feng Lai (ORCID |
| Source: | Education and Information Technologies. 2025 30(17):24787-24814. |
| Availability: | Springer. Available from: Springer Nature. One New York Plaza, Suite 4600, New York, NY 10004. Tel: 800-777-4643; Tel: 212-460-1500; Fax: 212-460-1700; e-mail: customerservice@springernature.com; Web site: https://link.springer.com/ |
| Peer Reviewed: | Y |
| Page Count: | 28 |
| Publication Date: | 2025 |
| Document Type: | Journal Articles Reports - Research |
| Education Level: | Higher Education Postsecondary Education |
| Descriptors: | Scaffolding (Teaching Technique), Reflection, Artificial Intelligence, STEM Education, Thinking Skills, Cognitive Processes, Engineering Education, College Students, Aviation Technology, Technology Uses in Education |
| DOI: | 10.1007/s10639-025-13758-4 |
| ISSN: | 1360-2357 1573-7608 |
| Abstract: | In today's knowledge society, where artificial intelligence (AI) technologies are increasingly integrated into educational contexts, designing intelligent learning systems with cognitive scaffolding functions has become a critical issue in learning technology research. Unmanned Aerial Vehicle (UAV) courses, which involve mechanical assembly, sensor integration, data processing, and flight control, present a highly integrated STEM learning task and an ideal context for examining the effectiveness of generative AI-assisted learning. This study employed a quasi-experimental design involving 64 first-year engineering students, who were randomly assigned to either an experimental group or a control group to participate in a six-week UAV-based project-oriented STEM course. The experimental group interacted with a GPT-based system featuring semantic prompts and dynamic feedback to support reflective questioning and strategic adjustment, while the control group engaged in paper-based reflection activities. Independent sample t-tests revealed that students in the experimental group significantly outperformed their counterparts in STEM literacy, levels of reflection, and higher-order thinking indicators. Furthermore, thematic analysis of students' reflection records and AI dialogues demonstrated that the GPT system effectively facilitated verbalized reflection and multi-level cognitive regulation. Students' engagement gradually shifted from operational procedures to conceptually driven strategic understanding. This study confirms the feasibility of AI-supported reflection and provides concrete theoretical and practical implications for the design and evaluation of future intelligent learning systems. |
| Abstractor: | As Provided |
| Entry Date: | 2026 |
| Accession Number: | EJ1501366 |
| Database: | ERIC |
| Abstract: | In today's knowledge society, where artificial intelligence (AI) technologies are increasingly integrated into educational contexts, designing intelligent learning systems with cognitive scaffolding functions has become a critical issue in learning technology research. Unmanned Aerial Vehicle (UAV) courses, which involve mechanical assembly, sensor integration, data processing, and flight control, present a highly integrated STEM learning task and an ideal context for examining the effectiveness of generative AI-assisted learning. This study employed a quasi-experimental design involving 64 first-year engineering students, who were randomly assigned to either an experimental group or a control group to participate in a six-week UAV-based project-oriented STEM course. The experimental group interacted with a GPT-based system featuring semantic prompts and dynamic feedback to support reflective questioning and strategic adjustment, while the control group engaged in paper-based reflection activities. Independent sample t-tests revealed that students in the experimental group significantly outperformed their counterparts in STEM literacy, levels of reflection, and higher-order thinking indicators. Furthermore, thematic analysis of students' reflection records and AI dialogues demonstrated that the GPT system effectively facilitated verbalized reflection and multi-level cognitive regulation. Students' engagement gradually shifted from operational procedures to conceptually driven strategic understanding. This study confirms the feasibility of AI-supported reflection and provides concrete theoretical and practical implications for the design and evaluation of future intelligent learning systems. |
|---|---|
| ISSN: | 1360-2357 1573-7608 |
| DOI: | 10.1007/s10639-025-13758-4 |
