Experiments on the localisation of cooking recipes content using semantic food descriptions
C. Stahl, B. Gateau, and K. Ferrini
in the 15th International Workshop on Semantic and Social Media Adaptation and Personalization, Virtual, Zakynthos, Greece; 29-30 October 2020, art. no. 9248466, ISBN: 978-172815919-5, 2020
The LIFANA Nutrition Solution helps elderly people maintaining a healthy BMI as their metabolism is changing with age and their eating habits eventually need to be reconsidered. LIFANA providespersonalized, weekly meal plans that helps users to prevent undernutrition or overweight, targetingthe total daily calories consumed and proteins. Mixed dishes or multi-ingredient foods represent the majority of items in diets worldwide. Despite the reliable data on the quantity and quality of nutrients and other components, there is not a harmonized and standardized method to use this data considering the recipes. For LIFANA we created an extensive recipe database with semantic annotation,linking the ingredients of each recipe to Food Composition databases to infer their nutrients. Within Europe, the recipes need to be localized, which means not only translated, but also linked to different national FCDBs. This article reports on our experience to solve this issue using semantic food descriptions and similarity measures.