| Sumario: | Background: Although existing studies suggest that AI chatbots hold potential as feedback tools in educational settings, there remains a significant gap in the literature regarding pedagogically grounded frameworks or guidelines for their effective implementation. Therefore, there is very little experimental research on how to use an AI chatbot based on a pedagogical approach. Objectives: This study proposed a conceptual framework grounded in a hybrid intelligence feedback model for the use of AI chatbots as pedagogical feedback tools and aimed to examine its applicability and effectiveness within a higher education programming course. Method: An experimental pre‐test/post‐test study involving 36 undergraduate students was conducted to evaluate the effectiveness of the proposed model and its underlying design principles for integrating AI chatbots as pedagogically grounded feedback tools in educational settings. Results and Conclusions: Theory‐grounded AI chatbots based on the proposed hybrid intelligence feedback model and its design principles significantly improved learning more than the general‐purpose AI chatbot in programming class. Theory‐grounded AI chatbots can be an effective feedback tool in improving students' skills in self‐evaluation, critical thinking, and regulating learning strategies. General‐purpose AI chatbot feedback may cause "metacognitive laziness," harming learning performance. Implications: The article indicates the need for further research and validation to ensure effective implementation and address challenges associated with AI's potential inaccuracies. Lay Summary: What is Already Known About This Topic ○There has been a growing body of research examining AI chatbot use for providing educational feedback.○Theoretical frameworks guiding AI chatbot use based on LLMs remain scarce and are still in the early stages.What This Paper Adds ○This paper proposed a conceptual framework based on hybrid intelligence in educational contexts.○This paper demonstrates how to integrate AI chatbots into educational settings as a feedback tool.○Customised AI chatbots based on the proposed model significantly improved learning.○Customised AI chatbots provide effective dialogic feedback and prevent metacognitive laziness.Implications for Practice and/or Policy ○Conceptual frameworks based on hybrid intelligence promote the potential of AI chatbots within educational settings.○The instructor should maintain ultimate decision‐making control, ensuring ethical and trustworthy AI chatbot implementation in education.○More research on different domains of education is needed to validate the model.
|
|---|