SoylentNews is people
SoylentNews
An algorithm developed at Carnegie Mellon University makes it easier to determine if someone has faked an Amazon or Yelp review or if a politician with a suspiciously large number of Twitter followers might have bought and paid for that popularity.
The method, called FRAUDAR, marks the latest escalation in the cat-and-mouse game played by online fraudsters and the social media platforms that try to out them. In particular, the new algorithm makes it possible to see through camouflage that fraudsters use to make themselves look legitimate, said Christos Faloutsos, professor of machine learning and computer science.
In real-world experiments using Twitter data for 41.7 million users and 1.47 billion followers, FRAUDAR fingered more than 4,000 accounts not previously identified as fraudulent, including many that used known follower-buying services such as TweepMe and TweeterGetter.
Bad news for the nascent astroturfing industry.
(Score: 0) by Anonymous Coward on Friday September 09 2016, @05:24PM
MoE for pretty much all of the polls are 5-9% right now. That is a pretty big range and lets room for interpretation (by design, I think someone like NBC can figure out how to do a poll by now). If they really had them in in the 1-2% range I could give them a bit more credence. One major aggregate poll is using data from May as a bellweather of how the election is going.
Usually until about 1-2 weeks out there is surprisingly 20% or so people who 'dont know'. But it almost always ends up 50/50. The news stations make it seem like it is close and all over the place. They *need* viewers to sell to their customers. The whole news media is imploding. No one wants print anymore. People are cutting the cord. Sound bites rule the internet. Investigative journalism takes time and large amounts of resources. If someone gave you 1 million dollars to invest. Would you put money into a news media company? You would think long and hard about that.