Enhancing self-regulated learning and higher-order thinking skills in virtual reality: the impact of ChatGPT-integrated feedback aids

This study explores the integration of ChatGPT technology into Virtual Reality (VR) learning environments to support self-regulated learning (SRL) strategies and foster higher-order thinking skills (HOTS). Utilizing a randomized controlled trial (RCT) design, 81 undergraduate students were randomly assigned to either an experimental group with GPT-feedback-supported VR learning or a control group with traditional feedback-supported VR learning. The VR learning environment focused on embedded IoT tasks, structured into six learning units aligned with Bloom's taxonomy. Results indicate that the experimental group demonstrated significantly higher cognitive levels across memory, understanding, and application tasks compared to the control group. Notably, GPT feedback markedly improved problem-solving and critical thinking skills, though its impact on creativity was limited. This limitation may be attributed to the directive nature of GPT feedback or the structured scope of learning tasks, which may not have encouraged open-ended creative exploration. SRL abilities were also significantly improved in the experimental group, highlighting the efficacy of GPT feedback in promoting self-reflection, goal setting, and strategy adjustment. The findings underscore the potential of integrating generative AI technologies like ChatGPT into VR learning environments to provide targeted, real-time feedback, thus addressing limitations of traditional VR feedback mechanisms. This integration supports deeper engagement and more effective learning outcomes, particularly in problem-solving and critical thinking, providing valuable insights for future educational technology implementations.