Evaluating the Efficacy of AI-Generated Inquiry-Based Lesson Plans in Science

This study aims to investigate the effectiveness of artificial intelligence in creating inquiry-based lesson plans for science education in the context of Turkey. An exploratory design was used to achieve this goal. The subject matter of middle school science was treated as a case and ChatGPT was asked to create lesson plans by specifying the objectives and duration of the lessons. Then, the plans were evaluated by the researchers, considering the rubric of the Guidelines for Assessing Inquiry-based Lesson Plans developed by Borda-Carulla and Harmen (2012). The researchers of this study evaluated the lesson plans separately, and the internal consistency coefficient was calculated as 0.83. The results suggest that the artificial intelligence-generated lesson plans were aligned with the course objectives, incorporated real-world contexts, and promoted an inquiry-based learning environment. Despite these strengths, the results of this study also suggest that some areas need to be improved, such as providing structured feedback and fostering curiosity.