NutriNLP: Advancing Personalized Nutrition with Natural Language Processing and Accelerating SDGs

Objectives: This study presents the design and development of an AI-driven platform using natural language processing tools for personalized nutritional assessment namely NutriNLP, and a Telegram chatbot designed for the healthy menu recommendations.

 

Method: This platform employs a Pellet-based nutritional ontology and Semantic Web Rule Language (SWRL) to provide weekly food menu suggestions based on user input, including weight, height, age, gender, activity level, and allergies. The chatbot were developed using the Methontology and Agile methodologies to generate personalized diet plans, and validated by nutritionists and respondents.

 

Results: Results show the effectiveness of these systems in leveraging extensive nutritional databases and personalized algorithms to provide accurate and actionable dietary advice. According to the findings, nutritionists' acceptance is 70% while the general users' acceptance is 86.67% which indicates a moderate acceptance level and possibility for improvement, especially in system performance.

 

Conclusions: The development of the NutriNLP chatbot marks a significant step forward in making personalized dietary recommendations accessible to the wider community. Its ability to calculate and classify food recommendations based on BMI, BMR, activity levels, and allergies demonstrates the practical benefits of combining artificial intelligence with semantic web technologies.

 

Research Implications: These advancements highlight the transformative potential of AI in enhancing Sustainable Development Goals (SDGs), including SDG 2 (Zero Hunger), SDG 3 (Good Health and Well-Being), and SDG 12 (Responsible Consumption and Production).

 

Originality/Value: The developed chatbot extracts the effective personalized nutritional assessment called NutriNLP which is designed to assist families in identifying, addressing nutritional problems and improving dietary habits.