Physical protection education was legislated by the Ministry of Education, Science and Technology (MEST) in November 2010. KINAC (Korea Institute of Nuclear Nonproliferation and Control) was designated as the exclusive institution for physical protection education and training by MEST in October 2011, and it has since functioned as the sole institution responsible for this critical aspect of nuclear security education in the country. Over the past decade, KINAC has undertaken a variety of training initiatives aimed at enhancing the capabilities of nuclear operators’ physical protection personnel. Furthermore, it has consistently pursued annual curriculum revisions based on insights gleaned from surveys and workshops. In conventional curriculum assessments, general surveys often rely on Likert scale or short-answer questions as primary indicators, mainly due to their ease of data processing. Descriptive questions, while capable of capturing diverse opinions, have historically been relegated to a secondary role owing to the inherent challenges associated with data analysis. While physical protection education has made concerted efforts to solicit diverse opinions through descriptive questions, difficulties in organizing and leveraging this valuable data have resulted in it primarily serving as reference material. This study introduces a novel approach by employing ChatGPT, a chatbot, to conduct a comprehensive analysis of the descriptive questions from the physical protection education survey administered in the first half of 2023. The primary objective is to formulate a robust plan for curriculum enhancement based on a wide spectrum of opinions. Following the completion of physical protection training by 2,014 individuals in the first half of 2023, a survey was distributed, yielding an impressive response rate of 95.7% with 1,927 respondents. Chatbots were harnessed to extract major keywords and perform frequency analyses on approximately 360 responses to descriptive questions in the survey. The analysis revealed that certain keywords emerged with notable frequency, in the following order: “drone” (mentioned 51 times), “access management” (mentioned 28 times), “inspection and search” (mentioned 27 times), and “cybersecurity” (mentioned 20 times). Further analysis of these major keywords and related content revealed a consensus among trainees that there is a pressing need to incorporate topics addressing drone threats and responses, as well as strategies to fortify access management into the curriculum. This study underscores the potential to harness standardized data analysis techniques to synthesize and integrate trainees’ subjective opinions, thereby providing a solid foundation for the refinement of the curriculum.

• Junghyun Na(Korea Institute of Nuclear Nonproliferation and Control (KINAC)) Corresponding author