Generative AI as a Dialogic Partner: Enhancing Multiple Perspectives, Reasoning, and Argumentation in Science Education with Customized Chatbots

Abstract This study investigates the potential of customized generative AI (GenAI) chatbots to foster dialogic learning and argumentation in science education. Framed by Bakhtin’s theory of heteroglossia emphasizing the interplay of multiple voices in discourse, a customized chatbot called Dialogic Science Teacher (DST) was deliberately designed to embody dialogic learning principles. This instructional approach positions GenAI as a dialogic partner rather than an authoritative knowledge provider. Using a case study approach, 21 students from two high schools interacted with DST to explore socioscientific issues as they learned physics, chemistry, and biology. Analysis of students’ chatlogs revealed four prominent dialogic characteristics: perspective-taking, reasoning, arguing, and creative thinking. Qualitative findings illustrated how dialogic interactions with DST were characterized by students in critically reflecting, reasoning, arguing, and developing innovative ideas and alternative perspectives in response to challenging scientific problems. Quantitative findings further demonstrated high percentages of these dialogic characteristics in both schools, thus indicating DST’s reach in facilitating dialogic interaction among the students. These findings underscore the significance of embedding dialogic learning principles into GenAI tools, highlighting their potential to encourage critical thinking, argumentation, and co-construction of knowledge in science classroom discourse. The study offers both theoretical and practical insights to ongoing discussions on GenAI’s role as a collaborative learning partner in science education.