Evaluating a GPT-powered tutor in secondary science education using a fuzzy comprehensive approach

Artificial intelligence is shaping almost every sphere of our lives and revolutionizing how we live and work. Education has the potential to harness the capabilities of this new technological wave and provide students an enhanced learning experience. In this context, the purpose of this paper is to investigate how high school students evaluate a GPT-powered tutor in science education using a fuzzy comprehensive method. Students interacted with the GPT-tutor both during weekly computer lab sessions and at home during the school year 2024–2025 and used it, among other things, for problem-solving in science, concept clarification, and self-assessment quizzes. Teachers provided guiding prompts to ensure consistent use and monitored students’ actions. The GPT—tutor evaluation was based on four criteria: students’ engagement, students’ performance, perceived enjoyment, and personalized learning. The survey showed that students have positive experience interacting with the tutor. Yet there is room for improvement, mainly in the areas of perceived enjoyment, personalized learning, and students’ performance. These results can be used as a guide to build more advanced AI—powered tutors that can provide students a better learning experience and consequently lead them to enhanced perceived learning outcomes. The value of this study lies in the integration of a GPT -powered tutor into high school science curriculum over an extended period of time and in the application of the Fuzzy Comprehensive Evaluation as a method to systematically capture students’ perceptions regarding students’ engagement, students’ performance, perceived enjoyment and personalized learning.