Building and using chatbots in the process of self-studying physics to improve the quality of learners' knowledge

The adoption of chatbots in education is steadily increasing, offering a myriad of benefits to learners engaging in self-directed study. However, the reliability of information provided by chatbots poses certain obstacles, particularly in subjects with high academic content such as physics. This study proposes a five-step process for constructing chatbots, enabling educators to independently develop chatbots to support self-learning among students. This process focuses on enabling chatbots to autonomously respond to physics-related inquiries, a capability often lacking in pre-built chatbots. A new chatbot for physics lessons on the conservation of energy law was developed by applying this methodology. To assess the feasibility and effectiveness of the developed chatbot, we conducted a pedagogical experimental study involving 100 tenth grade students divided into control and experimental groups. To ensure comparability between the groups, students were selected based on their physics grades and teacher feedback. Experimental data was collected through online feedback forms and a 45-minute physics test, processed using statistical techniques. The results indicate a high level of readiness among participants to utilize chatbots for self-learning and acknowledge their beneficial impact. Furthermore, students' knowledge quality improved with chatbot usage, affirming the feasibility and effectiveness of incorporating chatbots into physics education. These findings also validate the proposed five-step chatbot development process as rational and applicable.