SENTIMENT ANALYSIS OF TWITTER AND AMAZON DATA USING R PROGRAMMING

Abstract

The advancement in the field of Internet, digital and social media has increased data sets to larger extent. Sentiment Analysis is the methodology of computationally identifying and categorizing opinions expressed in a piece of text, in order to determine whether the opinion writer's attitude towards a particular topic, product etc. is positive, negative, or neutral. Real-time sentiment analysis is a challenging machine learning task, due to scarcity of labeled data and sudden changes in sentiment caused by real-world events that need to be instantly interpreted. In this project I propose solutions to save user time that they spend reading all the opinions on a particular topic or going through reviews about a product. And, help them make a better an instant informed decision. The attempt is to develop a system which could aggregate the reviews and opinions from various web sources using machine learning algorithm and provide an unbiased insight of consumer sentiments towards a product. I have used R programming techniques to build a generalized solution for data extraction, data mining, data analysis and data visualization from web sources for evaluating User Sentiments towards a program or product. The experiment has been conducted on below two areas:  Sentiments of people towards Make in India initiative.  Customer Sentiments towards Baby products in Amazon. Data used in this study are tweets extracted for Make In India campaign from Twitter and online customer reviews for baby products collected from Amazon.com. The different Data Analytics techniques are used to extract or discover knowledge from the tweets and posted reviews so as to generate interesting insights of user’s attitude towards an event or a particular product. My research covers work ranging from real time stream data processing, real time content search, event detection, link mining, behavior mining, and sentiment analysis. I will also feature my ongoing system research that aims to support user-friendly real time online data analytics using publicly available content.