SALES PREDICTION IN TOURISM INDUSTRY USING DATA MINING

Using a significant quantity of data gathered from a variety of sources, the tourism and travel industry is working to improve the quality of its services. Because of how simple it is to acquire the opinions, assessments, and experiences of a variety of visitors, the planning of tourism has become more sophisticated and rich. Therefore, one of the biggest challenges that the tourism industry has is figuring out how to utilise the data that has been collected to identify the preferences of tourists. Unfortunately, some of the comments made by users are both irrelevant and difficult to interpret, making it difficult to make recommendations based on them. Aspect-based sentiment categorization algorithms have shown considerable potential in terms of overcoming the noise. There hasn’t been a lot of study done on aspect-based emotion combined with categorization so far. The purpose of this study is to propose a framework for an aspect-based sentiment classification and recommendation system. Not only will it identify the aspects in a highly efficient manner, but it will also be able to complete classification tasks with a high level of accuracy utilising machine learning methods such as naive Bayes and Decision Tree. The performance of the framework has been tested by running tests using real-time datasets from Yelp and foursquare. The framework assists travellers in finding the best location, hotel, and restaurant in a city.