Twitter Sentiment Analysis Based on US Presidential Election 2016

Abstract

Twitter is among the most popular social networking Web sites today [1], with approximately 317 million monthly active users (Quarter 3 2016). Of these, 67 million users are from the USA. Twitter being a micro-blogging platform is widely used by people to express their opinions. Approximately, 500 million tweets are posted in a day, which is around 6000 tweets per second. Assuming, even one-tenth of these tweets reflect an emotion that results in a lot of people-generated data, which can prove to be a treasure trove of information if studied carefully. We intend to perform sentimental analysis on Twitter data of the US Presidential Election 2016 and then overlay our findings with respect to the two main candidates: Hillary Clinton and Donald Trump with the actual election result, to be able to categorically state whether Twitter can be used as a proper indication of any election.