Term of Award

Spring 2018

Degree Name

Master of Science in Computer Science (M.S.)

Document Type and Release Option

Thesis (restricted to Georgia Southern)

Copyright Statement / License for Reuse

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.


Department of Computer Sciences

Committee Chair

Wen-Ran Zhang

Committee Member 1

Andrew Allen

Committee Member 2

James Harris


In the age of social media, everyone has the ability to post their thoughts and feelings about several topics on the Internet for the world to see. Major social media platforms such as Facebook, Twitter, and Instagram are used to connect users across the globe to share photos and discuss trending topics. Trending topics can include sociopolitical issues or restaurant, movie and product reviews. Given the vast amount of data accumulated through the use of these platforms, sentiment analysis is a natural language process technique that can be used to assess public opinion of said topics. Sentiment analysis also has application potential in marketing and politics. Businesses can use it to discover public opinion of their products in real-time and understand how to better market their products to target consumers. Political analysts can use sentiment analysis to discover the likability of candidates for office amongst voters, which could aid in predicting the probability of winning elections.

In this paper, Twitter data was used to conduct sentiment analysis to gauge public opinion regarding Android and iPhone devices. Additionally, data visualization techniques were used to help tell the story of the data and present it in a pictorial view. Anaconda and Jupyter environments were used to develop and execute Python code to query against Twitter’s API, retrieve relevant tweets regarding iPhone and Android devices, transform and manipulate the data, and provide several graphical depictions of the result set. A system architecture diagram was presented to display the inner workings and flow process of the experiment. Lastly, the experiment conducted a comparison between Twitter’s sentiment polarity classifier and the ANEW dictionary to determine which device was favored amongst users.

Research Data and Supplementary Material