Scoring and Assessment Medium for Hotels and Restaurants Using Machine Learning

Abstract

At long last, businesses are making use of recommendation programmes to provide clients a curated set of options across a variety of categories. They are flexible and may be used to a wide range of scenarios since they are designed to provide customer-specific suggestions (like restaurants or tourist sites). There are a number of useful approaches to data management that can be utilised to improve the efficiency and effectiveness of recommendation processes and to address any issues that may occur. This work proposes a Machine Learning (ML) approach to the problem of personalising recommendations for restaurants from TripAdvisor.com. Guests make advantage of the hotel's amenities and provide constructive criticism. Natural Language Processing (NLP) is included for every hotel in order to analyse and categorise all previous user comments (both positive and negative) about that hotel. Then, the percentage of comments as a whole is tallied and recorded. Before receiving recommendations, customers must select the characteristics of a restaurant that speak to them; after acceptable hotels have been located, the information will be examined to decide which restaurant has the highest scores. The consumer may use the restaurant's structure to find the most highly rated hotel. In order to decipher the tone and distinguishing characteristics of user feedback, the authors suggest an emotional score metric built on top of a natural language processing system. Natural Language Processing (NLP) is a kind of machine learning that use the analysis, interpretation, and inference capabilities of the human language in order to solve problems. It was found that the proposed NLP algorithm excels over the state-of-the-art methods. This is supported by the evaluation outcomes. The purpose of this research paper is to produce a more comprehensive and reliable directory of area restaurants. The results and analysis of the research demonstrate the reliability of the method.