qz.com: "Facebook needs to hand over its algorithm if it really wants to end fake news"
On Sept. 5, 2006, Facebook transformed from a technology platform into a media company. That was the day the social media site replaced its chronological list of friends’ updates with its algorithmic news feed.
Since then, Facebook has decided everything its users—now totaling 1.8 billion on a monthly basis—see in their unique feeds. “Once [Facebook] got into the business of curating the newsfeed rather than simply treating it as a timeline, they put themselves in the position of mediating what people are going to see. They became a gatekeeper and a guide,” wrote Tim O’Reilly, a Silicon Valley investor and publisher, in a Medium post. “It’s their job. So they’d better make a priority of being good at it.”
Full article: qz.com
http://qz.com/847640/facebook-needs-to-hand-over-its-algorithm-if-it-really-wants-to-end-fake-news/
Hi Ted,
After preprocessing stage and tokenizing the text, several machine learning methods can used, such as Naive Bayes, SVM, Multilayer Perceptron, DT, etc.
HTH.
Samer
I think that is is useful to gain access to a good labeled publicly available for fake versus real news articles.
then, the above steps of feature extraction can be performed before machine learning.
- Badges
- Science topic
- Similar topics
- Philosophy
- Ethics