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.
Fakebox has a variety of utilities:
- Warn users before they share questionable content on your platformÂ
- Ensure your article content is impartial and your titles are not clickbait
- Analyze ad placement to determine how often ads are placed on questionable sites
- Give your manual content moderation a head start or helping hand
What Fakebox checks
Fakebox checks the following aspects of an article. You must provide at least one property to be checked, but the more information Fakebox is given, the more useful the results will be.
- Title: Can be clickbait or biased
- Content: The textual content of an article can be analyzed to determine if its written like real news or not
- Domain name: Some domains are known for hosting certain types of content and Fakebox knows about the most popular sites
Get started
- Make sure you have Docker running with at least 2 CPUs and 4GB RAM.
- Run this code in your terminal to start the box:
MB_KEY="YOURKEYHERE"
docker run -p 8080:8080 -e "MB_KEY=$MB_KEY" machinebox/fakebox
- Go to http://localhost:8080/ in your browser to see what your box can do
Updating Fakebox
If you already have Fakebox installed, you can update it with the following:
docker pull machinebox/fakebox:latest
