Assessment of Interests in Learning and Applying Machine Learning among Nutrition Students

Abstract: Nutrition students possess a solid foundation in food and nutrition knowledge, as well as relevant practical applications. Still, in the latest era of artificial intelligence, machine learning (ML) is essential for enhancing nutrition care processes and evaluating food quality. The study was to assess the interests of undergraduate and postgraduate nutrition students in learning and applying machine learning in the nutrition domain, and to understand their overall perception of the compulsory essential learning of ML for better technical applications in the same subject. Students with good academic backgrounds, analytical research skills, and fundamental machine-learning knowledge were included in the study. An open-ended questionnaire was used as a data collection tool for each participant, and Jamovi software was used for data analysis. Reliability and principal component analysis, followed by exploratory factor analysis, were done to determine the factors related to the students' interest and perception of using ML in nutrition. Keywords: Machine learning, Dietary assessment, Precision nutrition, Data science, Artificial intelligence. JEL Classification Number: I12, I21, I23