Scholarlink

<p>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.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Generative AI as a reflective scaffold in a UAV-based STEM project: A mixed-methods study on students’ higher-order thinking and cognitive transformation

  • 期刊论文

  • 发表日期：

    2025年9月4日

查看全文
  • Shih-Yeh Chen,
  • Wei-Cheng Chen,
  • Chin-Feng Lai

摘要

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.