Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/csinva/news-title-bias

Scraping and analyzing political bias in news titles using data from allsides.com
https://github.com/csinva/news-title-bias

bias natural-language-processing news politics python scraper

Last synced: 2 months ago
JSON representation

Scraping and analyzing political bias in news titles using data from allsides.com

Host: GitHub
URL: https://github.com/csinva/news-title-bias
Owner: csinva
Created: 2020-12-30T04:15:33.000Z (about 4 years ago)
Default Branch: master
Last Pushed: 2024-05-09T21:30:12.000Z (8 months ago)
Last Synced: 2024-10-07T13:41:53.204Z (3 months ago)
Topics: bias, natural-language-processing, news, politics, python, scraper
Language: HTML
Homepage: http://csinva.io/news-title-bias/app/
Size: 7.35 MB
Stars: 2
Watchers: 3
Forks: 2
Open Issues: 0
Metadata Files:
- Readme: readme.md

Awesome Lists containing this project

README

        # Scraping data on news title bias

Different sources cover the same news in very different ways! This project scrapes a dataset of article titles, sources, political leanings, and text from curated articles on [allsides.com](https://www.allsides.com/unbiased-balanced-news).

![](https://csinva.io/news-title-bias/app/assets/img/screenshot.jpeg)

The [scrape_data](https://github.com/csinva/news-title-bias/blob/master/notebooks/01_scrape_data.ipynb) notebook scrapes the data and saves it into a pandas dataframe (cached in the [data](data) folder).

The [data_to_html](https://github.com/csinva/news-title-bias/blob/master/notebooks/02_data_to_html.ipynb) notebook loads that dataframe into an html file, which can be viewed in [this app](https://csinva.io/news-title-bias/app/).

This data could also be useful for all kinds of tasks, such as classifying bias of different titles as well as trying to learn to translate between the same title with different political leanings.

# Reference

- uses data from [allsides.com](https://www.allsides.com/unbiased-balanced-news)

- horizontal timeline from [codyhouse](https://codyhouse.co/gem/horizontal-timeline)

- made by [@csinva_](https://twitter.com/csinva_)