SENTIMENT ANALYSIS ON TOURIST REVIEWS FOR PLACE RECOMMENDATION USING WORD EMBEDDINGS

Abstract

Multi-label sentence classification is a very popular technique to categorize text into several classes now-adays. The classification process may vary based on the type of text used such as tourist review, crime data, weather forecast data, accident data, airline services etc. Text data has become an important part of data analytics thanks to advances in natural language processing that transform unstructured text into meaningful data. Individuals utilize online different websites, pages, portals etc to express their interests, opinions or reviews regarding the user experience they had while using any product or services. And majority time the reviews of the users in the online world serves as references and recommendation for other user’s weather to use the particular product or not based on positive and negative reviews of the same product or service. We would be using a combination of Word2Vec and Glove which we suppose individually is powerful natural language processing techniques for sentiment analysis on tourist data. Here With this dissertation we would like to focus more on the problem that similar words cause during the processing of text, in the proposed work we will be more focused words that are used in similar ways to result in having similar representations, naturally capturing their meaning along with positive and negative review classification using machine learning.