Enhancing Education Outcomes Integrating Augmented Reality and Artificial Intelligence for Education in Nutrition and Food Sustainability

Background/Objectives: The integration of Augmented Reality (AR) and Artificial Intelligence (AI) in educational applications presents an opportunity to enhance learning outcomes in young users. This study focuses on ARFood, a serious game designed to teach Generation Alpha about nutritional health and environmental sustainability. The objective is to evaluate and improve the effectiveness of the app’s AI-driven feedback mechanisms in achieving specific educational goals in these domains. Methods: ARFood features two AI-powered Non-Player Characters (NPCs), each programmed to evaluate virtual shopping carts created by users. The nutritional NPC provides feedback on dietary choices, while the sustainability NPC assesses environmental impacts. Ninety-three participants were involved, generating 83 virtual carts that were evaluated by both NPCs. Each NPC’s feedback was assessed for alignment with five predefined educational objectives per theme using a zero-shot RoBERTa classifier. An iterative process was employed to refine the NPC prompts, increase the weight of underrepresented objectives, and re-evaluate virtual carts until all objectives were satisfactorily addressed. Results: Initial evaluations revealed uneven alignment across educational objectives, particularly in areas such as resource conservation and balanced diet planning. Prompt refinement led to a significant improvement in feedback quality, with the final iterations demonstrating comprehensive coverage of all educational objectives. Conclusions: This study highlights the potential of AR and AI in creating adaptive educational tools. Iterative prompt optimization, supported by zero-shot classification, was effective in enhancing the app’s ability to deliver balanced, goal-oriented feedback. Future applications can leverage this approach to improve educational outcomes across various domains.