Systematic Review of Nutritional Recommendation Systems

Abstract

In recent years, the promotion of healthy habits, and especially diet-oriented habits, has been one of the priority interests of our society. There are many apps created to count calories based on what we eat, or to estimate calorie consumption according to the sport we do, or to recommend recipes, but very few are capable of giving personalized recommendations. This review tries to see what studies exist and what recommendation systems are used for this purpose, over the last 5 years in the main databases. Among the results obtained, it is observed that the existing works focus on the recommendation system (usually collaborative filtering), and not so much on the description of the data or the sample analyzed; the indices used for the calculation of calories or nutrients are not specified. Therefore, it is necessary to work with open data, or well-described data, which allows the experience to be reproduced by third parties, or at least to be comparable. In recent years, the promotion of healthy habits, and especially diet-oriented habits, has been one of the priority interests of our society.

Recommendation Systems in Nutrition Field: A Scoping Review (Preprint)

“…Compared to previous review studies of RSs used in general health or food management [54][55][56] , we conducted a scoping review specifically focused on NRSs due to the unique role of nutrition in improving health. Two previous systematic reviews of NRSs summarized the design purposes, technical characteristics, main modules and applied platforms of NRSs, primarily focusing on computational methods, AI models and recommendation algorithms [26,57] . Additionally, a systematic review of the NRSs for polycystic ovary syndrome explored the challenges and limitations of using and designing these systems and algorithms, particularly the NRSs providing food recommendations [58] .…”