https://github.com/walidalsafadi/bbc-news-sentiment-analysis

Using BBC News data to analyze the sentiment of news, from title and description.
https://github.com/walidalsafadi/bbc-news-sentiment-analysis

exploratory-data-analysis machine-learning news nlp sentiment-analysis textpreprocessing

Last synced: 4 months ago
JSON representation

Using BBC News data to analyze the sentiment of news, from title and description.

• Host: GitHub
• URL: https://github.com/walidalsafadi/bbc-news-sentiment-analysis
• Owner: WalidAlsafadi
• License: mit
• Created: 2024-08-12T12:06:43.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2024-08-22T14:21:49.000Z (about 1 year ago)
• Last Synced: 2025-06-05T03:56:46.131Z (4 months ago)
• Topics: exploratory-data-analysis, machine-learning, news, nlp, sentiment-analysis, textpreprocessing
• Language: Jupyter Notebook
• Homepage:
• Size: 8.75 MB
• Stars: 4
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • Changelog: news_sentiment_analysis.csv
  • License: LICENSE

Awesome Lists containing this project

README

          
# BBC_News

![News](https://www.thesun.co.uk/wp-content/uploads/2024/05/bbc-news-logo-171735604.jpg)

# About Dataset:

### Context

Self updating dataset. It collects RSS Feeds from BBC News using a Kernel: https://www.kaggle.com/gpreda/bbc-news-rss-feeds.

The Kernel is run with a fixed frequency and the dataset is updated using the output of the Notebook.

These datasets can be viewed as classification or regression tasks. The classes are ordered and not balanced (e.g. there are much more normal wines than excellent or poor ones).

### Content

BBC News RSS Feeds. The data contains the following columns:

- title

- pubDate

- guid

- link

- description

### Collection method

Uses requests_html and BeautifulSoup to collect RSS Feeds from BBC News site.

### Acknowledgements

The content is proprietary of BBC.

### Inspiration

Use the data to analyze the sentiment of news, from title and description.