Computer Algorithm Can Recognize Sarcasm

[Acturus]

Computer Algorithm Can Recognize Sarcasm (Which Is Just Soooo Cool)
http://www.popsci.com/technology/art...ich-soooo-cool

http://www.popsci.com/files/imagecac.../sarcasm01.jpg

The pursuit of machine intelligence means we have to come up with ways to communicate with our computers in a way both entities can understand. But while computers process verbal commands in a straightforward fashion, humans tend to use more sophisticated speech forms, employing slang or symbols to convey an idea. So an Israeli research team has developed a machine algorithm that can recognize sarcasm.

SASI, a Semi-supervised Algorithm for Sarcasm Identification, can recognize sarcastic sentences in product reviews online with pretty astounding 77 percent precision. To create such an algorithm, the team scanned 66,000 Amazon.com product reviews, with three different human annotators tagging sentences for sarcasm. The team then identified certain sarcastic patterns that emerged in the reviews and created a classification algorithm that puts each statement into a sarcastic class.

The algorithms were then trained on that seed set of 80 sentences from the collection of reviews. These annotated sentences helped the algorithm learn what sorts of words and patterns distinguish sarcastic remarks – those that mean the opposite of what they literally convey, or that convey a sentiment inconsistent with the literal reading.

They then turned the algorithm loose on an evaluation set. Pattern evaluation efficiency scored accurately 81 percent of the time, while the overall precision of the pattern recognition/sarcasm categorizing algorithm was accurate in 77 percent of instances. Not bad for a computer’s first shot at interpreting the human sense of humor.

This isn’t all just so your Roomba gets the joke when you tell it it sucks. Computer programs that can recognize sarcastic statements could generate better personalized content and make better recommendations to human users by not mistaking a product review titled “keep your receipt” with a sound piece of online shopping advice. It could also benefit opinion-mining systems that troll the Web trying to measure public sentiment about a product or idea.

I for one welcome our new dry-witted terminator overlords.

[Correction]

Simpsons did it.

[Khajit]

But can it see why kids love cinnamon toast crunch?

[Obev]

Sure it can.

[Max™]

What a useful comment, Obev.

[Kaisha]

What a useful comment, Obev.

Really? Why?

[Max™]

Got the first customer already!

[Avanarius]

I don't see why they don't already have this available as a program, text based sarcasm is way easier to detect on the internet then through speech.

[Alleya]

80%, that's pretty good considering the average person on the internet can't even pick out 1 sarcastic statement.

[Shalyn]

But what will it do for this poor man?

[Max™]

[Darus Grey]

I don't see why they don't already have this available as a program, text based sarcasm is way easier to detect on the internet then through speech.

What? Not even close.

Sarcasm in speech has a distinct speech intonation pattern that's detectable specifically as sarcasm, including monotone(aka deadpan).

Machines can detect sarcasm in speech with 99.99~% accuracy and have been able to for decades, the processing power needed to run real time speech analysis held it back more than the ability to detect it, which is actually the case with many speech parsing programs...we've had the methods set aside for decades on how to parse speech, but processing power isn't there yet except on low-end super-computers.

Spoken speech is honestly the simplest thing about language.

[Avanarius]

What? Not even close.

Sarcasm in speech has a distinct speech intonation pattern that's detectable specifically as sarcasm, including monotone(aka deadpan).

Machines can detect sarcasm in speech with 99.99~% accuracy and have been able to for decades, the processing power needed to run real time speech analysis held it back more than the ability to detect it, which is actually the case with many speech parsing programs...we've had the methods set aside for decades on how to parse speech, but processing power isn't there yet except on low-end super-computers.

Spoken speech is honestly the simplest thing about language.

80%, that's pretty good considering the average person on the internet can't even pick out 1 sarcastic statement.

lmao....one / nothing

[Obev]

What? Not even close.

Sarcasm in speech has a distinct speech intonation pattern that's detectable specifically as sarcasm, including monotone(aka deadpan).

Machines can detect sarcasm in speech with 99.99~% accuracy and have been able to for decades, the processing power needed to run real time speech analysis held it back more than the ability to detect it, which is actually the case with many speech parsing programs...we've had the methods set aside for decades on how to parse speech, but processing power isn't there yet except on low-end super-computers.

Spoken speech is honestly the simplest thing about language.

You clearly won't be needing this algorithm.

[Skjie]

This thread is quite the mine field.

[Darus Grey]

You clearly won't be needing this algorithm.

Which only proves my point.

[Obev]

I'm not even sure who's being sarcastic or not at this stage.

[Avanarius]

I'm not even sure who's being sarcastic or not at this stage.

Of course you aren't.....

[Grey Jorildyn]

They ought to have it analyze transcriptions of some Bush speeches from the past decade and see what comes up...

[Guitarman]

skynet.