Red Feed vs. Blue Feed: Differences in COVID-19 Digital News Coverage based on Partisan Lean Open Access
Fan, Alex (Spring 2021)
Published
Abstract
The rise of the COVID-19 Pandemic has sparked changes to the global landscape on both micro-political and macro-political levels. The ramifications of the pandemic, in many ways, has been a function of polarized rhetoric from traditional media institutions. Many studies have already examined the effects of polarized information on people’s individual behavior in relation to the pandemic. However, not as much attention has been spent exploring the variation in content and contextual representations underlying the polarized information. This project contributes to the broader literature by constructing and leveraging a novel corpus of approximately 300,000 COVID-19 digital news articles that spans an entire year of the pandemic, representing the most comprehensive set of its kind to date. In addition, this project also created a novel hand-labeled dataset of approximately 1,500 articles, with classes that delineate an article’s orientation toward micro-political or macro-political actions in combating COVID-19. Analysis of these datasets show a small shift in content based on the political lean of the news source, with right-leaning news sources spending a greater proportion of their content on state-level coverage than left-leaning news sources do. Moreover, right-leaning news sources tend to portray important public health measures such as mask-wearing and social distancing in a negative light, particularly by associating them with non-science. Overall, this work presents a new, more comprehensive angle of studying political media discourse in the context of a pandemic.
Table of Contents
INTRODUCTION ...................................................................................................................... 1
LITERATURE REVIEW............................................................................................................... 3
DATA AND METHODS ............................................................................................................. 6
General Overview .................................................................................................................................................................. 6
Topic Model Analysis..........................................................................................................................................................11
Classifier Section..................................................................................................................................................................17
Word Embedding Analysis ...............................................................................................................................................25
DISCUSSION.......................................................................................................................... 29
CONCLUSION ........................................................................................................................ 33
REFERENCES ......................................................................................................................... 36
About this Honors Thesis
| School | |
|---|---|
| Department | |
| Degree | |
| Submission | |
| Language |
|
| Research Field | |
| Keyword | |
| Committee Chair / Thesis Advisor | |
| Committee Members |
Primary PDF
| Thumbnail | Title | Date Uploaded | Actions |
|---|---|---|---|
|
|
Red Feed vs. Blue Feed: Differences in COVID-19 Digital News Coverage based on Partisan Lean () | 2021-04-13 03:00:13 -0400 |
|
Supplemental Files
| Thumbnail | Title | Date Uploaded | Actions |
|---|