Abstract
AbstractGood nutrition and balance dietary pattern play vital roles of leading a healthy lifestyle. Prior studies showed that the healthy diet can successfully reduce the risk of chronic diseases (e.g., type 2 diabetes and cancer) and bring other well‐documented benefits. Existing food recommendation models, however, often solely rely on user's feedback (e.g., click and purchase data), which aims to optimize Click‐Through Rate (CTR) but ignores the importance of health needs of users. Intuitively, a healthy diet recommendation requires a comprehensive consideration of different kinds of information, such as nutrition, ingredients and cooking methods. In this study, by collecting the data from FoodData Central (FDC), recipe websites, and scientific literature, we construct a heterogeneous graph, Food‐Nutrition‐Recipe Graph (FNRG), by integrating information of nutrition, food (ingredients), and recipes. A random walk based graph mining approach is proposed to meet the health needs of users. Experiments results show that the proposed method can successfully address the health information needs for people who suffer from chronic diabetes.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Proceedings of the Association for Information Science and Technology
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
