Integrating generative artificial intelligence in the design of scientific inquiry for middle school students

This study aims at exploring the role of generative artificial intelligence (AI) in scientific inquiry and giving some implications for teaching scientific inquiry by examining the interactions between secondary students and AI during the design of open-ended physics experiments. A generative AI assistant was developed to support this process and a total of seven students were encouraged to use AI across 17 sessions. Thus, the researchers collected and analyzed conversations between the participants and AI, interview with the participants, and their reports. The results show that students' requests to the AI were identified with five categories: variable setting, experimental materials, procedure, analysis/results, and knowledge. As well, their queries were divided into information retrieval and request of feedback in terms of the purpose of request. The interaction frequencies and patterns with AI were influenced by the familiarity of the given topic and their perceptions about AI. Thus, this study gave some implications how AI can be used to enhance students' abilities relevant to scientific inquiry.