Zomato Review Analysis Using Machine Learning

Abstract

Restaurant ratings and reviews have a noteworthy influence on shaping the public’s perception of a restaurant and influencing the dining decisions of individuals. With the rise of online platforms and review websites, it is now easier for customers to share their experiences and opinions about restaurants. Potential diners can easily access information about the quality of food, service, atmosphere, and value for money offered by a restaurant. Many customers visit a restaurant based on reviews given by the customer or other app users. India has a rich culinary heritage and offers a diverse range of cuisines that cater to different tastes and preferences. The restaurant industry in India is growing rapidly, and new restaurants are popping up all the time, offering customers an ever-increasing variety of dining options. Starting a new restaurant can be challenging, especially in a highly competitive market like India, where there are already many established restaurants. Major challenges that persist in the industry comprise elevated real estate expenses, escalating food prices, insufficient skilled labour, and customer acquisition. The system aims to perform sentimental analysis and exploratory data analysis on Zomato reviews. Sentimental analysis is performed using the SVM approach to determine the accuracy of the sentiment model. The model would deliver the top three cuisines in a location based on sentiment analysis, which would help new restaurants make decisions. The system shows factors affecting restaurant businesses by doing data analysis on various parameters of the dataset. The SVM model has adequate accuracy.