News for hackers. Stuff that matters.
Re:Show HN: AI tool reads privacy policies, tells you which ... by michaelaiello on Thursday November 10, 2011 @06:54PM (#3222555)
Works just like spam filtering: We're using a naive Bayesian classifier with training data. Built and tested a custom extractor that makes the most sense for the legalese of privacy policies.

Ideas: email me at michaelaiello (at) michaelaiello.com

Re:Show HN: AI tool reads privacy policies, tells you which ... by raphman on Friday November 11, 2011 @03:34AM (#3223910)
Might I suggest adding at least this sentence to the training set: "We sell your private information."

Your Policizer happily tells me that the sentence means "They DO NOT sell your private information."