{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T20:10:01Z","timestamp":1772050201026,"version":"3.50.1"},"reference-count":36,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:00:00Z","timestamp":1759104000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Public Investment Program of the Greek Ministry of Education and Religious Affairs","award":["80860"],"award-info":[{"award-number":["80860"]}]}],"content-domain":{"domain":["www.mdpi.com"],"crossmark-restriction":true},"short-container-title":["Computers"],"abstract":"<jats:p>Recipes available on the web often lack nutritional transparency and clear indicators of dietary suitability. While searching by title is straightforward, exploring recipes that meet combined dietary needs, nutritional goals, and ingredient-level preferences remains challenging. Most existing recipe search systems do not effectively support flexible multi-dietary reasoning in combination with user preferences and restrictions. For example, users may seek gluten-free and dairy-free dinners with suitable substitutions, or compound goals such as vegan and low-fat desserts. Recent systematic reviews report that most food recommender systems are content-based and often non-personalized, with limited support for dietary restrictions, ingredient-level exclusions, and multi-criteria nutrition goals. This paper introduces DietQA, an end-to-end, language-adaptable chatbot system that integrates a Knowledge Graph (KG), Retrieval-Augmented Generation (RAG), and a Large Language Model (LLM) to support personalized, dietary-aware recipe search and question answering. DietQA crawls Greek-language recipe websites to extract structured information such as titles, ingredients, and quantities. Nutritional values are calculated using validated food composition databases, and dietary tags are inferred automatically based on ingredient composition. All information is stored in a Neo4j-based knowledge graph, enabling flexible querying via Cypher. Users interact with the system through a natural language chatbot friendly interface, where they can express preferences for ingredients, nutrients, dishes, and diets, and filter recipes based on multiple factors such as ingredient availability, exclusions, and nutritional goals. DietQA supports multi-diet recipe search by retrieving both compliant recipes and those adaptable via ingredient substitutions, explaining how each result aligns with user preferences and constraints. An LLM extracts intents and entities from user queries to support rule-based Cypher retrieval, while the RAG pipeline generates contextualized responses using the user query and preferences, retrieved recipes, statistical summaries, and substitution logic. The system integrates real-time updates of recipe and nutritional data, supporting up-to-date, relevant, and personalized recommendations. It is designed for language-adaptable deployment and has been developed and evaluated using Greek-language content. DietQA provides a scalable framework for transparent and adaptive dietary recommendation systems powered by conversational AI.<\/jats:p>","DOI":"10.3390\/computers14100412","type":"journal-article","created":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T14:01:39Z","timestamp":1759154499000},"page":"412","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["DietQA: A Comprehensive Framework for Personalized Multi-Diet Recipe Retrieval Using Knowledge Graphs, Retrieval-Augmented Generation, and Large Language Models"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1446-9377","authenticated-orcid":false,"given":"Ioannis","family":"Tsampos","sequence":"first","affiliation":[{"name":"Department of Electrical & Computer Engineering, Hellenic Mediterranean University, 71410 Heraklion, Greece"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5685-0480","authenticated-orcid":false,"given":"Emmanouil","family":"Marakakis","sequence":"additional","affiliation":[{"name":"Department of Electrical & Computer Engineering, Hellenic Mediterranean University, 71410 Heraklion, Greece"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,29]]},"reference":[{"key":"ref_1","unstructured":"Toledo, R.Y., Alzahrani, A.A., and Martinez, L. (2019). A Food Recommender System Considering Nutritional Information and User Preferences, Springer."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Azzi, R., Despres, S., and Diallo, G. (2020, January 7\u201310). NutriSem: A Semantics-Driven Approach to Calculating Nutritional Value of Recipes. Proceedings of the WorldCIST 2020, Budva, Montenegro.","DOI":"10.1007\/978-3-030-45688-7_20"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Chen, M., Jia, X., Gorbonos, E., Hong, C.T., Yu, X., and Liu, Y. (2020). Eating Healthier: Exploring Nutrition Information for Healthier Recipe Recommendation. arXiv.","DOI":"10.1016\/j.ipm.2019.05.012"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"122166","DOI":"10.1016\/j.eswa.2023.122166","article-title":"A systematic review on food recommender systems","volume":"238","author":"Bondevik","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"101313","DOI":"10.1016\/j.patter.2025.101313","article-title":"A Systematic Survey of Natural Language Processing for the Greek Language","volume":"6","author":"Bakagianni","year":"2025","journal-title":"Patterns"},{"key":"ref_6","unstructured":"Trattner, C., and Elsweiler, D. (2017). Food Recommender Systems: Important Contributions, Challenges and Future Research Directions. arXiv."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1007\/s10844-017-0469-0","article-title":"An overview of recommender systems in the healthy food domain","volume":"50","author":"Tran","year":"2018","journal-title":"J. Intell. Inf. Syst."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Orue-Saiz, I., Kazarez, M., and Mendez-Zorrilla, A. (2021). Systematic Review of Nutritional Recommendation Systems. Appl. Sci., 11.","DOI":"10.3390\/app112412069"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"100484","DOI":"10.1016\/j.patter.2022.100484","article-title":"Applications of knowledge graphs for food science and industry","volume":"3","author":"Min","year":"2022","journal-title":"Patterns"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"100743","DOI":"10.1016\/j.websem.2022.100743","article-title":"Health-guided recipe recommendation over knowledge graphs","volume":"75","author":"Li","year":"2023","journal-title":"J. Web Semant."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"881","DOI":"10.1177\/01655515221151139","article-title":"Construction of recipe knowledge graph based on user knowledge demands","volume":"51","author":"Cui","year":"2023","journal-title":"J. Inf. Sci."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"3701","DOI":"10.1007\/s13369-020-05236-5","article-title":"CookingQA: Answering Questions and Recommending Recipes Based on Ingredients","volume":"46","author":"Khilji","year":"2021","journal-title":"Arab. J. Sci. Eng."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1016\/j.ins.2018.12.032","article-title":"Interactive natural language question answering over knowledge graphs","volume":"481","author":"Zheng","year":"2019","journal-title":"Inf. Sci."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Chatterjee, U., Giunchiglia, F., Madalli, D.P., and Maltese, V. (2016). Modeling Recipes for Online Search. On the Move to Meaningful Internet Systems: OTM 2016 Conferences, Springer. LNCS.","DOI":"10.1007\/978-3-319-48472-3_37"},{"key":"ref_15","unstructured":"Gao, F., Zhao, X., Xia, D., Zhou, Z., Yang, R., Lu, J., Jiang, H., Park, C., and Li, I. (2025). HealthGenie: Empowering Users with Healthy Dietary Guidance through Knowledge Graph and Large Language Models. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Chen, Y., Subburathinam, A., Chen, C., and Zaki, M.J. (2021, January 8\u201312). Personalized Food Recommendation as Constrained Question Answering over a Large-scale Food Knowledge Graph. Proceedings of the Fourteenth ACM International Conference on Web Search and Data Mining (WSDM\u201921), Online.","DOI":"10.1145\/3437963.3441816"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"\u0141awrynowicz, A., Wr\u00f3blewska, A., Adrian, W.T., Kulczy\u0144ski, B., and Gramza-Micha\u0142owska, A. (2022). Food Recipe Ingredient Substitution Ontology Design Pattern. Sensors, 22.","DOI":"10.3390\/s22031095"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Senath, T., Athukorala, K., Costa, R., Ranathunga, S., and Kaur, R. (2024). Large Language Models for Ingredient Substitution in Food Recipes using Supervised Fine-tuning and Direct Preference Optimization. arXiv.","DOI":"10.1016\/j.nlp.2025.100177"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Bajaj, V., Panda, R.B., Dabas, C., and Kaur, P. (2018, January 29\u201331). Graph Database for Recipe Recommendations. Proceedings of the 7th International Conference on Reliability, Infocom Technologies and Optimization (ICRITO), Noida, India.","DOI":"10.1109\/ICRITO.2018.8748827"},{"key":"ref_20","unstructured":"Tang, Y.S., Zheng, A.H., and Lai, N. (February, January 27). Healthy Recipe Recommendation Using Nutrition and Ratings Models. Proceedings of the AAAI 2019, Honolulu, HI, USA."},{"key":"ref_21","unstructured":"The New York Times (2025, July 27). Nytimes\/Ingredient-Phrase-Tagger: Extract Structured Data from Ingredient Phrases Using Conditional Random Fields. Available online: https:\/\/github.com\/nytimes\/ingredient-phrase-tagger."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1109\/TPAMI.2019.2927476","article-title":"Recipe1M+: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Images","volume":"43","author":"Biswas","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1007\/978-3-031-85572-6_5","article-title":"A Knowledge Graph Question Answering System for Personalized Nutrition and Recipes Recommendation","volume":"Volume 611","author":"Tsampos","year":"2025","journal-title":"Pervasive Computing Technologies for Healthcare: 18th EAI International Conference, PervasiveHealth 2024, Heraklion, Crete, Greece, 17\u201318 September 2024, Proceedings, Part I"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Trattner, C., and Elsweiler, D. (2017, January 3\u201317). Investigating the Healthiness of Internet-Sourced Recipes. Proceedings of the WWW Conference, Perth, Australia.","DOI":"10.1145\/3038912.3052573"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Huang, X., Zhang, J., Li, D., and Li, P. (2019, January 11\u201315). Knowledge Graph Embedding Based Question Answering. Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining (WSDM\u201919), Melbourne, VIC, Australia.","DOI":"10.1145\/3289600.3290956"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Gharibi, M., Zachariah, A., and Rao, P. (2020). FoodKG: A Tool to Enrich Knowledge Graphs Using Machine Learning Techniques. Front. Big Data, 3.","DOI":"10.3389\/fdata.2020.00012"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Zioutos, K., Kondylakis, H., and Stefanidis, K. (2023). Healthy Personalized Recipe Recommendations for Weekly Meal Planning. Computers, 13.","DOI":"10.3390\/computers13010001"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Ribeiro, R., Batista, F., Pardal, J.P., Mamede, N.J., and Pinto, H.S. (2006, January 12\u201315). Cooking an Ontology. Proceedings of the AIMSA 2006, Varna, Bulgaria.","DOI":"10.1007\/11861461_23"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Haussmann, S., Seneviratne, O., Chen, Y., Ne\u2019eman, Y., Codella, J., Chen, C.-H., McGuinness, D.L., and Zaki, M.J. (2019, January 26\u201330). FoodKG: A Semantics-Driven Knowledge Graph for Food Recommendation. Proceedings of the International Semantic Web Conference (ISWC), Auckland, New Zealand.","DOI":"10.1007\/978-3-030-30796-7_10"},{"key":"ref_30","unstructured":"Fatemi, B., Duval, Q., Girdhar, R., Drozdzal, M., and Romero-Soriano, A. (2023). Learning to Substitute Ingredients in Recipes. arXiv."},{"key":"ref_31","unstructured":"Qi, Z., Yu, Y., Tu, M., Tan, J., and Huang, Y. (2023). FoodGPT: A Large Language Model in Food Testing Domain with Incremental Pre-training and Knowledge Graph Prompt. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Zhou, P., Min, W., Fu, C., Jin, Y., Huang, M., Li, X., Mei, S., and Jiang, S. (2024). FoodSky: A Food-oriented Large Language Model that Passes the Chef and Dietetic Examination. arXiv.","DOI":"10.2139\/ssrn.4972042"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"100465","DOI":"10.1016\/j.smhl.2024.100465","article-title":"ChatDiet: Empowering personalized nutrition-oriented food recommender chatbots through an LLM-augmented framework","volume":"32","author":"Yang","year":"2024","journal-title":"Smart Health"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Tsampos, I., and Marakakis, E. (2024, January 26\u201328). Querying Knowledge Graphs in Greek Language. Proceedings of the 17th International Conference on PErvasive Technologies Related to Assistive Environments, Crete, Greece.","DOI":"10.1145\/3652037.3652072"},{"key":"ref_35","first-page":"1677","article-title":"d2kg: An integrated ontology for knowledge graph-based representation of government decisions and acts\u2014The Greek Programme Diavgeia case","volume":"15","author":"Serderidis","year":"2024","journal-title":"Semant. Web"},{"key":"ref_36","unstructured":"Tsampos, I., and Marakakis, E. (2023, January 28\u201331). A Medical Question Answering System with NLP and Graph Database. Proceedings of the HeDAI 2023 Workshop, Co-Located with EDBT\/ICDT 2023 Joint Conference, Ioannina, Greece."}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/10\/412\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T14:18:35Z","timestamp":1759155515000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/10\/412"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,29]]},"references-count":36,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["computers14100412"],"URL":"https:\/\/doi.org\/10.3390\/computers14100412","relation":{},"ISSN":["2073-431X"],"issn-type":[{"value":"2073-431X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,29]]}}}