Abstract
The widespread use of online review websites has revolutionized how consumers choose restaurants, particularly in popular tourist destinations like Los Angeles, where a vast range of dining options is readily available. However, the sheer abundance of similar cuisine offerings can be overwhelming. To address this challenge, this study used Python Selenium to web crawl Tripadvisor for gathering data about Los Angeles restaurants. Relevant information from user reviews was extracted and analyzed utilizing natural language processing techniques to classify restaurants based on cuisine, price, and customer reviews and ratings. This classification allowed for the identification of distinct dining preferences, providing insights into restaurant selection in tourist-heavy areas. With the application of cosine similarity, the analysis further led to the development of a recommendation system specific to consumers’ needs and preferences. This study thus offers a new approach to improving restaurant discovery and decision-making in busy urban centers in Los Angeles.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have