[sharjeel]

Thanks to the HN comments which assured that it is important. Otherwise after reading the first sentence and processing it with standard sensational filtering regex of my brain, I wouldn't have proceeded forward.

"In a [stunning|amazing] discovery that overturns [years|decades|centuries] of [textbook teaching|beliefs|research] [researchers|scientists] at the <XYZ Lab> have discovered that the <PQR premise> holds false."

[Mahn]

Pointless weekend project idea: A service that scans articles for matching regexes to classify the level of bullshit of what you are reading. It could even be a browser extension with the bullshit indicator automatically shown for each page in its icon.

[slowmovintarget]

http://www.blablameter.com/index.php

(Article has an index of 0.14 -- not BS)

[nkozyra]

This just requires some NLP to identify obvious hyperbole. In fact, you could probably just watch HN for long enough, establish some training data and have this happen somewhat automatically for you in the browser.

[nitrogen]

Basically a spam filter trained on news instead of email. I like it. Could we get SpamAssassin to do this? (Does it still exist?)

[foxhedgehog]

upvoted this, big N

[eterm]

http://www.quackometer.net/

edit to add: Not mine, just a site I used to know about that fit this description.

[cholantesh]

Ran it on this(http://www.naturalnews.com/049944_vegetable_oil_omega-3_pest...) NN article and it's still processing 20 minutes later. I'd like to think it's breaking whatever scale is being applied to it, but it's most likely the connection speed in my office. :P

[BurningFrog]

Neural network!

[WalterSear]

"Medical scientists hate it!"

[degenerate]

Haha, I never thought of what a regex match would look like for headlines, that's pretty damn hilarious :)

[seanp2k2]

I'd think you'd have better luck using bayes with some clever stemming / tokenization :)