Fakebox analyzes news articles to assess whether they are likely to be real news or not. By looking at a range of available aspects of an article (title, content and URL) using built-in machine learning models and a manually curated database, Fakebox can successfully identify fake news.
This capability has a variety of utilities:
Fakebox checks the following aspects of an article. Users must provide at least one property to be checked, but the more information Fakebox is given, the more useful the results will be.
The best way to get started with Fakebox is to spin up a local instance and play with it.
docker run -p 8080:8080 -e "MB_KEY=$MB_KEY" machinebox/fakebox
http://localhost:8080/in your browser to access the Fakebox console