Proposal for a Novel Recipe Generation Approach Using Inverse TF-IDF and Generative AI

Authors

  • Mutsumi Kodama Kagoshima women's college
  • Taishi Nemoto University of Kochi

DOI:

https://doi.org/10.52731/liir.v006.455

Keywords:

Artificial Intelligence, Education, Recipe 3.0, LLMs for cooking, nutritional analysis, democratization of culinary innovation, ChatGPT

Abstract

This paper proposes a novel recipe generation system that integrates an inverse term frequency–inverse document frequency (TF-IDF) approach with generative artificial intelligence (AI) to balance creativity with practicality in home cooking. While conventional recipe recommendation systems tend to focus on commonplace recipes or staple ingredients, this study adopted an inverse approach by focusing on low-IDF ingredients and leveraging them as the foundation for generating highly reproducible recipes. Utilizing GPT-4, the system automatically constructs prompts that reflect user preferences and cooking conditions, enabling the generation of context-sensitive recipes. A lightweight web-based demo system was developed, allowing users to input two ingredients and receive original recipe suggestions along with cosine similarity scores in real time. Even when users input seemingly unrelated ingredients, the system provides composite recipe outputs, demonstrating its creative flexibility. This approach uncovers the latent creative potential in common ingredients and suggests broad applicability in the food industry, nutritional planning, and culinary education. By combining generative AI with statistical ingredient analysis, the proposed method offers a new intelligent support model for everyday cooking practices.

References

Kanwipa Lertsumruaypun, Satoshi Nakamura, Chiemi Watanabe "Association of Onomatopoeia and Recipe Terminology in Recipe Search Systems" ,Information Processing Society of Japan Research Report, IPSJ SIG Technical Report, 2010

Yasuyuki Akazawa, Hisashi Miyamori, "Proposal of a Cooking Recipe Search System Considering Refrigerator Ingredients" ,DEIM Forum 2012

Kyosuke Ikeijiri,Yuichi Sei, Hiroyuki Nakagawa, Yasuyuki Tahara, Akihiko Ohsuga, " A Proposal of Recommendation Agents for Surprising Recipes", Journal of the Institute of Electronics, Information and Communication Engineers D Vol. j98-D No.6 pp.971-981, 2015

Yasuhiro Mori, Eriko Yoshimura, Seiji Tsuchiya, Koichi Watanabe, "Construction of a Cooking Concept Base for Cooking Systems", Information Processing Society of Japan Vol. 2014-ISC-174 No.6, 2014.

Yuka Shidochi,Tomokazu Takahashi,Ichiro Ide,Hiroshi Muras " Discovery of replaceable materials from cooking recipe texts ", The 22nd Annual Conference of the Japanese Society for Artificial Intelligence, 2008

Yusuke Tagawa,Arata Tanaka,Yuya Minami,Daichi Namikawa,Michio Shimomura,Takahira Yamaguchi" Supporting Diet Therapy Based on Japanese Linked Data ", The 27th Annual Conference of the Japanese Society for Artificial Intelligence, 2013

Hidekazu Shiozawa, "A casual recipe search interface considering the priority of ingredients", Transactions of the Institute of Electronics, Information and Commu-nication Engineers, Vol. J94-A, No. 7, pp. 458-466, © Institute of Electronics, In-formation and Communication Engineers, 2011

Shihono Karime, Atsushi Fujii, "Recipe Retrieval Considering Nutritional Balance", Proceedings of the 14th Annual Conference of the Association for Natural Language Processing, 2008

Mayumi Ueda, Kazuyuki Ishihara, Yasushi Hirano, Masashi Kajita, Kenji Mase, "A recipe recommendation method that reflects personal tastes based on ingredient usage history", Japan Database Society Letters Vol.6, No.4, 2008

Miki Kimura, “A Case Study for Text Classification by Employing a Weighted Variable TF-IDF”, Meiji University Literature Research Papers No. 48, 2018

Kihara, H., Ueda, M., and Nakajima, S. “A recipe recommendation method that considers the use of surplus ingredients”, DEIM Forum, E3-3, 2011

Mayumi Ueda, Kazuyuki Ishihara, Yasushi Hirano, Masashi Kajita, Kenji Mase, “A recipe recommendation method that reflects personal preferences based on ingre-dient usage history”, Symposium on Database and Web Information Systems DBWeb2007, 3C-3, 2007

Izumi Toda, Masaru Kakuma, “A computer-based cooking menu system - an ex-pert system for menu creation”, Information Processing Society of Japan SIG Technical Report, No.91-CH-10, pp.1–8, 1991

Hidekazu Shiozawa, “Interactive cooking recipe search by keywords and their priorities”, Interactive Cooking Recipe Search by Keywords and Their Priori-ties∗wiss2007

Motoki Moritaku, Yuanyuan Wang, “A proposal for a luxurious recipe recom-mendation method based on metadata analysis of cooking recipes”, DEIM2022 C24-4

Yamamoto Keita, Hinata Nasu, Kazuhiro Kazama "Method of adding metadata to recipes focusing on food arrangements" DEIM2020 P1-5 (day1 p70)

Downloads

Published

2025-10-02