Ruoyi Chen MSc Dissertation 2015/16

The TWITTERATI: Text Analysis of Twitter and other Social Media

Supervised by M.Hepple

Abstract

Nowadays, social media has become an important part of people's daily life benefited from the development of the Internet. These social media provide citizens a platform to disseminate and transfer information, or to show their opinions and thoughts on any topic that they interested in. A massive amount of electronic textual data produces by these social media provides large potential commercial value to everyone. It is significant to do sentiment analysis for finding people's opinions on these data.

In this project, the main goal is to classify people's opinion on whether the United Kingdom should leave the EU or not from Twitter data. The categorized result will be compared with poll data from YouGov . Lexicon-based method and machine learning method are used to do sentiment analysis.