Sometimes it ’s operose to tell when somebody online is complimenting you or being a douche bag . That ’s why a grouping of Israeli research worker excogitate the “ Semi - supervised Algorithm for Sarcasm Identification , ” a program that recognizes sarcastic statements with 77 percentage precision .
consort to Popular Science :
To create such an algorithm , the team run down 66,000 Amazon.com production reviews , with three different human annotators tagging sentences for satire . The squad then identify sealed sarcastic patterns that emerged in the reviews and created a classification algorithmic program that couch each statement into a sarcastic year . . . The algorithmic rule were then develop on that seed set of 80 sentences from the collection of reviews . These annotated sentences help the algorithm hear what form of Scripture and patterns distinguish sarcastic remark – those that entail the opposite of what they literally get , or that convey a sentiment inconsistent with the genuine recitation .
Even if the sarcasm detector can be used for the forces of goodness , it saddens me to think of a computer learning about human satire from Amazon brushup , I think every AI has to begin somewhere .
viaPopular Science[viaSlashdot , which has the full scientific composition ]
SciencesoftwareTechnology
Daily Newsletter
Get the best tech , skill , and culture news in your inbox day by day .
news program from the hereafter , save to your present .
You May Also Like
