Date of Award




Document Type

Master's Thesis

Degree Name

Master of Arts (MA)


Department of Mathematics and Statistics

Content Description

1 online resource (ii, 66 pages) : illustrations (some color)

Dissertation/Thesis Chair

Karin Reinhold

Committee Members

Martin Hildebrand, Yiming Ying


Elections, Machine learning, Social media, Probabilistic automata, Learning classifier systems

Subject Categories

Physical Sciences and Mathematics


This thesis is an introduction to the mathematical formalization of sentiment classification. It presents two popular probabilistic machine learning models to classify tweets downloaded from Twitter during the US Election Period, 2016. The thesis analyses accuracy of the two classification algorithms used. Namely, Multinomial Naïve Bayes and Bernoulli Naïve Bayes algorithms. Supervised learning approaches implemented in this thesis use approximately 600 manually labeled tweets containing information regarding the US presidential candidates. It is shown with 80% accuracy that majority of twitter users spoke in favor of Donald Trump before and after the presidential election through their tweets. We also discuss that further research in sentiment classification using advanced machine learning techniques will help to improve performance of the models, and to increase accuracy of results obtained in this thesis.