NORMA eResearch @NCI Library

Sentiment Classification of Current Public Opinion on BREXIT: Naïve Bayes Classifier Model vs Python’s TextBlob Approach

Shekhawat, Bhupender Singh (2019) Sentiment Classification of Current Public Opinion on BREXIT: Naïve Bayes Classifier Model vs Python’s TextBlob Approach. Masters thesis, Dublin, National College of Ireland.

[img]
Preview
PDF (Master of Science)
Download (1MB) | Preview

Abstract

Sentiment Analysis is playing a crucial role in technological world due to tremendous growth in the field of social media. The motivation regarding sentiment analysis comes from the fact that social media platforms like twitter provide a great platform which is used by general public to express their opinions about a product or an event. Such opinions provide an opportunity to researchers to work on data mining based on public reviews and opinion and provide critical insights helpful for organizations in better decision making. This paper discusses comparison in performances of Naïve Bayes Classifier Model and Python’s TextBlob library by carrying out sentiment classification on current public opinion on BREXIT. In order to achieve the objectives, natural language processing, concepts including regular expression library and count vectorization have been used. Also, Natural Language Toolkit library along with TextBlob library are used to clean the data and provide polarity score to the tweets respectively. Naive Bayes Classification algorithm is then introduced into the model after training it on Sentiment140 Twitter dataset to provide an accuracy comparison to that of the TextBlob. Therefore, useful insights are produced considering visualizations obtained from Tableau. Moreover, the results of this research provide an insight about public opinions of different countries about BREXIT. Also, the results will help British and Irish governments to formulate their foreign policies and internal policies in order to maintain their relationship with their major business friendly countries.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science

Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software

Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4150 Computer Network Resources > The Internet > World Wide Web > Websites > Online social networks
T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Telecommunications > The Internet > World Wide Web > Websites > Online social networks
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: CAOIMHE NI MHAICIN
Date Deposited: 11 Oct 2019 16:32
Last Modified: 11 Oct 2019 16:32
URI: http://trap.ncirl.ie/id/eprint/3856

Actions (login required)

View Item View Item