Adaptafood: an intelligent system to adapt recipes to specialised diets and healthy lifestyles Morales Garzón, Andrea Gutiérrez Batista, Karel Martín Bautista, María José Food computing Recipe Adaptation Word embedding Healthy diet Natural language processing Funding for open access charge: Universidad de Granada/CBUA. This research was partially supported by the Grant PID2021-123960OB-I00 funded by MICIU/AEI/10.13039/501100011033 and by ERDF/EU, and Grant TED2021-129402B-C21 funded by MICIU/AEI/10.13039/501100011033 and by the European Union NextGenerationEU/PRTR. It was also funded by “Consejería de Transformación Económica, Industria, Conocimiento y Universidades de la Junta de Andalucí­a” through a pre-doctoral fellowship program (Grant Ref. PREDOC_00298). In addition, this research has been partially supported by the project BAG-INTEL (Ref. 101121309) funded by the European Commission and the project CITIC-2024-06, funded by the Research Center for Information and Communication technologies of the University of Granada. This paper presents AdaptaFood, a system to adapt recipes to specifc dietary constraints. This is a common societal issue due to various dietary needs arising from medical conditions, allergies, or nutritional preferences. AdaptaFood provides recipe adaptations from two inputs: a recipe image (a fne-tuned image-captioning model allows us to extract the ingredients) or a recipe object (we extract the ingredients from the recipe features). For the adaptation, we propose to use an attention-based language sentence model based on BERT to learn the semantics of the ingredients and, therefore, discover the hidden relations among them. Specifcally, we use them to perform two tasks: (1) align the food items from several sources to expand recipe information; (2) use the semantic features embedded in the representation vector to detect potential food substitutes for the ingredients. The results show that the model successfully learns domain-specifc knowledge after re-training it to the food computing domain. Combining this acquired knowledge with the adopted strategy for sentence representation and food replacement enables the generation of high-quality recipe versions and dealing with the heterogeneity of diferent-origin food data. 2025-04-23T10:26:13Z 2025-04-23T10:26:13Z 2025-02-01 journal article Morales-Garzón, A., Gutiérrez-Batista, K., & Martin-Bautista, M. J. (2025). Adaptafood: an intelligent system to adapt recipes to specialised diets and healthy lifestyles. Multimedia Systems, 31(1), 1-24. https://doi.org/10.1007/s00530-025-01667-y https://hdl.handle.net/10481/103761 10.1007/s00530-025-01667-y eng http://creativecommons.org/licenses/by-nc-nd/4.0/ open access Attribution-NonCommercial-NoDerivatives 4.0 Internacional Springer Nature