News for hackers. Stuff that matters.
Re:An algorithm that can spot and kill Twitterbots before th... by tbirdz on Saturday August 24, 2013 @12:59PM (#6269120)
>falsely identifying accounts as fake only 0.0058 percent of the time (or about 6 out of 10,000)

That may sound impressive, but if there is 554,750,000 twitter users [1], 554750000 * (6/10000) is still 332,850 people who would have a false positive.

[1]: http://www.statisticbrain.com/twitter-statistics/

Re:An algorithm that can spot and kill Twitterbots before th... by random42 on Saturday August 24, 2013 @02:08PM (#6269323)
That is the bane of Machine Learning algorithms. They cannot be 100% accurate. That is why for destructive measures, you need to establish human oversight when using such algorithms.
Re:An algorithm that can spot and kill Twitterbots before th... by _greim_ on Saturday August 24, 2013 @06:10PM (#6269984)
However, humans are also machine learning algorithms, and may or may not have a better false positive rate than 0.0058%.