Ethan Elasky
This is my thesis for my Data Science honors course. It aims to compare Taiwanese media coverage of America and China using natural language processing techniques. This is informative in understanding polarization and media bias in Taiwan, which is largly split along differing attitudes about the threat posed to the island by the mainland's Communist regime. For more detailed information, see my Pre-Analysis Plan. Lucy Li is my advisor.
This repo contains a few subfolders which contain the elements of this project.
| Folder | Description |
|---|---|
data |
scraped article links in parquet and CSV format |
images |
image files used in the Jupyter Notebooks |
analysis |
Jupyter Notebooks containing data analysis |
scrapers |
website spiders (Scrapy), scrapers (Playwright), and preprocessing scripts |