Aspect-based sentiment analysis search engine for social media data

Abstract

Extraction of positive or negative opinions from any online content has received more consideration from researchers during the past decade, since the number of internet users that actively use online review sites, social networks and personal blogs to express their opinions has been growing. Sentiment analysis is the study of automated techniques for extracting sentiments from written languages making use of natural language processing tasks to thoroughly pre-process the data and extract polarity from the data. Customers who want to purchase products or services as well as business organizations, often rely on online reviews for knowing the overall user sentiment. Based on the sentiment, customers can choose whether or not to purchase a product while the organizations get an overall picture of their product. Aspect-based sentiment analysis helps in extraction of important features called aspects because knowing the polarity only is not sufficient. The proposed aspect-based sentiment analysis model uses polarity classification and sentiment extraction on reviews, and extracts the most interesting polarity aspects preferred by the customers automatically using both machine learning and deep learning algorithms. A search engine to pull out tweets and reviews relevant to user specified keyword is developed and corresponding interesting aspects are displayed.