NLP-BASED FOOD SUGGESTIONS SYSTEM – SMART HOMES
DOI:
https://doi.org/10.35543/indiarxiv.34Keywords:
Food Sysggestion System, Bert, Item SimilarityAbstract
With advanced AI, every industry is growing at rocket speed, while the smart home industry has not reached the next-generation level. A home can only be called a real smart home, when it is completely smart and understand what the residents want, and provide service in a timely manner. The residents should live in the house as if they are leaving in a motel while the house itself takes care of itself and give extra benefits to residents like providing food suggestions to the residents for everyday meals based on their taste, culture, weather, type of their food diet, their interest to try new recipes etc. Our system is an NLP Bert model-based similarity prediction model. The system ranks the recipes based on the similarity of the words and context. Recipes have similar ingredients and procedures are considered similar recipes. Overall, the system creates the top K number of recipes based n the number of days' history of eating habits and removes products that are similar to the recent m number of days to make sure the suggestions are not quite repetitive ( here m<<<<n).
References
Yashar Deldjoo, Fatemeh Nazary, Arnau Ramisa, Julian Mcauley, Giovanni Pellegrini, Alejandro Bellogin & Tommaso Di Noia, A Review of Modern Fashion Recommender Systems, https://arxiv.org/pdf/2202.02757.pdf
Nusrat Jahan Prottasha, Abdullah As Sami, Md Kowsher, Saydul Akbar Murad, Anupam Kumar Bairagi, Mehedi Masud, and Mohammed Baz, Transfer Learning for Sentiment Analysis Using BERT Based Supervised Fine-Tuning, https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9185586/
https://doi.org/10.3390/s22114157
Vishnu Nandakumar, Recommendation system using BERT embeddings, https://medium.com/analytics-vidhya/recommendation-system-using-bert-embeddings- 1d8de5fc3c56
D. Viji, and S. Revathy, A hybrid approach of Weighted Fine-Tuned BERT extraction with deep Siamese Bi – LSTM model for semantic text similarity identification, https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8735740/
https://doi.org/10.1007/s11042-021-11771-6
Xingyun Xie, Zifeng Ren, Yuming Gu and Chengwen Zhang, Text Recommendation Algorithm Fused with BERT Semantic Information, https://dl.acm.org/doi/abs/10.1145/3507548.3507582
Itzik Malkiel , Dvir Ginzburg, Oren Barkan, Avi Caciularu, Jonathan Weill, Noam Koenigstein, Interpreting BERT-based Text Similarity via Activation and Saliency Maps, https://dl.acm.org/doi/abs/10.1145/3485447.3512045
https://doi.org/10.1145/3485447.3512045
Allyson Ettinger, What BERT Is Not: Lessons from a New Suite of Psycholinguistic Diagnostics for Language Models. https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00298/43535/What-BERT-Is-Not-Lessons-from-a-New-Suite-of
https://doi.org/10.1162/tacl_a_00298
Semantic Similarity with BERT, https://keras.io/examples/nlp/semantic_similarity_with_bert/#inference-on-custom-sentences
James Briggs, BERT For Measuring Text Similarity, https://towardsdatascience.com/bert-for-measuring-text-similarity-eec91c6bf9e1
PAUL MOONEY , RecipeNLG (cooking recipes dataset, https://www.kaggle.com/code/paultimothymooney/explore-recipe-nlg-dataset
Kashish Ahuja, Mukul Goel, Sunil Sikka, and Priyanka Makkar, What-To-Taste: A Food Recommendation System, https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3670234
https://doi.org/10.2139/ssrn.3670234
Yasmin Beij, A Literature Review on Food Recommendation Systems to Improve Online Consumer Decision-Making, https://edepot.wur.nl/526224
Luís Rita, Building a Food Recommendation System, Towards data science, https://towardsdatascience.com/building-a-food-recommendation-system-90788f78691a
Thi Ngoc Trang Tran, Müslüm Atas, Alexander Felfernig, and Martin Stettinger, Journal of Intelligent Information Systems volume 50, pages 501–526 (2018), An overview of recommender systems in the healthy food domain, https://link.springer.com/article/10.1007/s10844-017-0469-0
https://doi.org/10.1007/s10844-017-0469-0
Pratiksha Ashok.Naik, International Journal of Innovative Science and Research Technology, ISSN No:-2456-2165, Volume 5, Issue 8, August – 2020
Florian Pecune1*, Lucile Callebert1 and Stacy Marsella1, Designing Persuasive Food Conversational Recommender Systems With Nudging and Socially-Aware Conversational Strategies, https://www.frontiersin.org/articles/10.3389/frobt.2021.733835/full
Downloads
Posted
Categories
License
Copyright (c) 2023 Divya Mereddy
This work is licensed under a Creative Commons Attribution 4.0 International License.
The authors own the copyright to their works deposited in IndiaRxiv and are licensed under Creative Commons Attribution 4.0 International Public License.
