Food recommendation based on semantic annotations and reference prescriptions: The SMART BREAK project

Food recommendation, as well as searching for health-related information, presents specific characteristics if compared with conventional recommender systems, since it often has educational purposes, to improve behavioural habits of users. In this paper, we presents a Food Recommendation System that aims at addressing some of the above mentioned issues, using a recipe dataset and annotations to propose menus according to user's preferences. Reference prescription schemes, e.g., compliant with nutritional guidelines, are defined to prepare suggested choices. The recommender system has been developed in the context of the SMART BREAK project, supported by a grant from Regione Lombardia in the field of "smart cities and communities" and related to the main topics of the 2015 World Exposition (EXPO2015, Milan, Italy), where the University of Brescia aimed at promoting healthy behavioural habits in nutrition.