The Semantics and Collocations Relation in Food Reviews

Authors

  • Fazel Keshtkar St. John's University
  • Ledong Shi St. John's University
  • Syed Ahmad Chan Bukhari St. John's University

DOI:

https://doi.org/10.32473/flairs.v34i1.128372

Keywords:

NLP semantic food review word2vec machine learning visualization

Abstract

Finding our favorite dishes have became a hard task since restaurants are providing more choices and va- rieties. On the other hand, comments and reviews of restaurants are a good place to look for the answer. The purpose of this study is to use computational linguistics and natural language processing to categorise and find semantic relation in various dishes based on reviewers’ comments and menus description. Our goal is to imple- ment a state-of-the-art computational linguistics meth- ods such as, word embedding model, word2vec, topic modeling, PCA, classification algorithm. For visualiza- tions, t-Distributed Stochastic Neighbor Embedding (t- SNE) was used to explore the relation within dishes and their reviews. We also aim to extract the common pat- terns between different dishes among restaurants and reviews comment, and in reverse, explore the dishes with a semantics relations. A dataset of articles related to restaurant and located dishes within articles used to find comment patterns. Then we applied t-SNE visual- izations to identify the root of each feature of the dishes. As a result, to find a dish our model is able to assist users by several words of description and their inter- est. Our dataset contains 1,000 articles from food re- views agency on a variety of dishes from different cul- tures: American, i.e. ’steak’, hamburger; Chinese, i.e. ’stir fry’, ’dumplings’; Japanese, i.e., ’sushi’.

Downloads

Published

2021-04-18

How to Cite

Keshtkar, F., Shi, L., & Bukhari, S. A. C. (2021). The Semantics and Collocations Relation in Food Reviews. The International FLAIRS Conference Proceedings, 34. https://doi.org/10.32473/flairs.v34i1.128372

Issue

Section

Special Track: Semantic, Logics, Information Extraction and AI