Ratnaparkhi, Kedar (2018) Recommender system for food in a restaurant based on Natural Language Processing and Machine Learning. Masters thesis, Dublin, National College of Ireland.
|
PDF (Master of Science)
Download (1MB) | Preview |
Abstract
Millions of customers post online reviews in the form of their own experience at restaurants. Some are positive while some are negative. Usually an overview of all the reviews is provided on the respective restaurant page. But this approach is hardly accurate or efficient. This research analyzes user reviews in restaurant domain, and then consolidates the information recommending the best dishes served to a customer at a restaurant. The system is developed using modern NLP techniques such as sentiment lexicon, sentiment scores, POS tagging to generate useful features and classify the information using Machine Learning classification algorithms such as KNN, Random Forest and SVM. The system achieved more than 93% accuracy across various experiments, with Random Forest performing best for the given dataset and SVM giving the best performance with a cross-validated dataset.
Actions (login required)
![]() |
View Item |