Very creative project! Congratulations!!
Thank you! :)
Show HN: I made a neural net that analyzes privacy policies
11–20 of 122 posts
Re: Show HN: I made a neural net that analyzes privacy policies
#12Hmm, I was trying to go through your A/B options but it didn't seem to register any click. So I started clicking repeatedly. Then, it processed those clicks on the first 7 items, giving you bad data. FYI.
Re: Show HN: I made a neural net that analyzes privacy policies
#13Hi guys! So as basis for my thesis on AI and NLP I've been working on a RRN-based text classifier that basically reads and analyzes privacy policies. It understands that "we don't share your data with third parties" is privacy friendly while "we may share your data with anyone" is a potential threat. I've then created this website with a bunch of analyzed services to showcase the most relevant info about each service…
Looks cool. It's a small point, but not pluralising words when the number is 1 shows attention to detail (e.g. 1 scandals for instagram).
Re: Show HN: I made a neural net that analyzes privacy policies
#14Telegram has a 105% score? Is that expected or a bug?
Re: Show HN: I made a neural net that analyzes privacy policies
#15Hmm, I was trying to go through your A/B options but it didn't seem to register any click. So I started clicking repeatedly. Then, it processed those clicks on the first 7 items, giving you bad data. FYI.
This just hit the frontpage so the server might be a bit overloaded, I'm sorry. Trying to resize resources right now. Thanks for the heads up, in the long term (ideally) noise shouldn't be a huge problem in a sufficiently large dataset (or at least I'm already expecting some noise haha)
Re: Show HN: I made a neural net that analyzes privacy policies
#16Telegram has a 105% score? Is that expected or a bug?
Bug, one of the components of the score is not properly normalized I think. I'll fix it as soon as I handle the traffic overload :)
Re: Show HN: I made a neural net that analyzes privacy policies
#17Telegram has a 105% score? Is that expected or a bug?
It should be pretty close to 100%, though, they seem to be super privacy friendly!
Re: Show HN: I made a neural net that analyzes privacy policies
#18Great work! Would also work as a browser plugin.
Re: Show HN: I made a neural net that analyzes privacy policies
#19This is interesting, but I wonder what a boilerplate privacy policy would score. Given the clustering of scores between 30 & 50% for what read like "our lawyers pulled the standard policy and billed us for 4 hours of minor tweaks", it seems like some of the most effective privacy advocacy would come by challenging the most common "dangerous sentences" in court.