Skip to content

Latest commit

 

History

History
22 lines (18 loc) · 896 Bytes

File metadata and controls

22 lines (18 loc) · 896 Bytes

Fakenews dataset analysis

Machine learning on a fake news data set. More information Analysis of a FakeNews dataset with Machine Learning.

Sample

Here is a sample of the dashboard.

fake news analysis dashboard

With machine learning services it was possible to automatically extract:

  • name of the author
  • language
  • article content
  • translation of the article to English
  • relevant terms (entity name recognition)
  • sentiment

Folders content

  • Python: the python scripts to scrape, process and load the news
  • Dataset: the news scraped and processed, exported as json text files
  • Resources: the newsletters downloaded from euvsdisinfo.eu
  • Jupyter: a juptyter notebook
  • kibana: the kibana dashboard