Penerapan Metode Naive Bayes untuk Klasifikasi Nilai Gizi Makanan

Abstract

Nutritional data analysis requires a computational method capable of producing fast, simple, and highly accurate classifications. Although many modern classification algorithms offer strong performance, several of them involve high computational complexity and require larger datasets to achieve optimal results. Naive Bayes is selected in this study because it performs effectively on small to medium-sized datasets, relies on a simple independence assumption between features, and is proven to be stable when processing numerical nutritional attributes such as energy, protein, fat, and carbohydrates. Furthermore, the algorithm consistently produces reliable outcomes when the data structure presents clear inter-class variations, which is commonly found in macronutrient-based food categories. This study aims to apply the Naive Bayes method to classify food categories based on nutritional values using RapidMiner. The research procedure includes data collection, preprocessing, label determination, model construction, and performance evaluation. The results show that the Naive Bayes model achieved an accuracy of 99.86%, with precision, recall, and F1-score values of 1.00, indicating highly optimal classification performance. These findings confirm that Naive Bayes is an appropriate and effective approach for nutritional data analysis, particularly for health applications, food recommendation systems, and nutrition education platforms