Trumping the Polls: Event Analysis During the 2016 Election Open Access

Shaban, Tarrek (2017)

Permanent URL: https://etd.library.emory.edu/concern/etds/jd472w54s?locale=en%255D
Published

Abstract

Since its introduction in 2006, Twitter has grown into an integral venue for political discourse. With this in mind, it is not surprising that Twitter and other social media services have played an important role in shaping the political debate during the 2016 presidential election. The dynamics of social media provide a unique opportunity to detect and interpret the pivotal events and scandals of the candidates quantitatively. This paper examines several text-based analysis to determine which topics have a lasting impact on the election for the two main candidates, Clinton and Trump. About 135.5 million tweets are collected over the six weeks prior to the election. From these tweets, topic clustering, keyword extraction, and tweeter analysis are performed to better understand the impact of the events occurred during this period. This analysis builds upon a social science foundation to provide another avenue for scholars to use in discerning how events detected from social media show the impacts of campaigns as well as campaign the election.

Table of Contents

1 Introduction 1

2 Background 4

2.1 Predicting Presidential Elections................. 4

2.1.1 Opinion Polling...................... 5

2.1.2 Fundimentals Models................... 7

2.1.3 2016 Cycle Accuracy ................... 9

2.2 Campaigns and Polling...................... 11

2.3 Corpus Considerations ...................... 12

2.4 Event Detection.......................... 14

3 Approach 15

3.1 Data Collection .......................... 15

3.1.1 Twitter Dataset...................... 16

3.1.2 News Dataset ....................... 18

3.2 Event Clustering ......................... 18

3.3 Extracting Meaning from Tweets ................ 23

3.3.1 Processing the Tweets .................. 24

3.3.2 Keyword Extraction ................... 25

4 Experiments 29

4.1 Exploring Top-Level Trends ................... 29

4.1.1 Volume of Tweets..................... 30

4.1.2 Sentiment of Tweets ................... 34

4.1.3 Win/Loss Synsets of Tweets............... 37

4.2 EventScoring........................... 38

5 Discussion 42

5.1 Presidential Election Debates .................. 43

5.2 Clinton's Email Scandals..................... 46

6 Conclusion 50

About this Honors Thesis

Rights statement
  • Permission granted by the author to include this thesis or dissertation in this repository. All rights reserved by the author. Please contact the author for information regarding the reproduction and use of this thesis or dissertation.
School
Department
Degree
Submission
Language
  • English
Research Field
Keyword
Committee Chair / Thesis Advisor
Committee Members
Last modified

Primary PDF

Supplemental Files