USE OF ARTIFICIAL INTELLIGENCE TO IDENTIFY AND CORRECT MISCONCEPTIONS ABOUT RADIATION

The expansion of nuclear technologies in various industries, combined with the constant threat of radiation-related incidents, highlights the urgent need for effective radiation education. This study is devoted to an empirical investigation of the effectiveness of artificial intelligence tools (neurological models of artificial intelligence) in detecting and correcting of artificial intelligence tools (neurological models of artificial intelligence) in detecting and correcting misconceptions about radiation (ionising radiation). We empirically evaluate the effectiveness of artificial intelligence (AI) tools in detecting and correcting these misconceptions among university students, focusing on different cognitive, cognitive-activity, and systemic-axiological levels. A pedagogical experiment was conducted with 168 students of Ukrainian universities using control questionnaires to assess the effectiveness of the selected artificial intelligence tools. The experiment involved presenting students with a series of statements designed to identify misconceptions related to factual knowledge (e.g., radiation units, background levels), conceptual understanding (e.g., the difference between radiation and radioactivity, effects of low-dose exposure), and application/evaluation (e.g., risk assessment, protective measures). AI tools, including natural language processing models for text analysis and machine learning algorithms for misconceptions classification, were used to provide personalised feedback and targeted corrective information. The results show that AI achieved high accuracy (80-98%) in eliminating misconceptions about factual knowledge. However, the effectiveness decreased for misconceptions requiring deeper conceptual understanding (73-78%) and is much lower for those involving complex knowledge assessment and application (24-36%). These findings indicate that while AI has significant potential to improve basic radiation literacy and provide automated feedback, its current capabilities are limited in addressing more multidimensional and complex misconceptions. Further research is needed to develop more sophisticated AI-based integrations that can effectively target higher-order cognitive skills and promote a more complete understanding of radiation science and its implications. This study contributes to this field by providing empirical evidence on the strengths and weaknesses of AI in radiation education, and offers practical recommendations for the further development and implementation of customised AI-based learning tools.