The world’s most accurate sarcasm-detecting algorithm just arrived. We’re all real impressed.
No, really, it is impressive. Sooooooo impressive, you guys. We already know — thanks to exhaustive and totally useful research into the communicative functions of sarcasm — that sarcasm can boost creativity by forcing you to think abstractly, and it can also help keep brains limber, improve communication, and aid in diagnosing cognitive problems. We’ve also heard the Secret Service is interested in this research, which is reassuring as f*ck.
Six years ago, a computer program was developed in Israel which could recognize sarcasm with 77% accuracy. Now David Bamman from UC Berkeley and Noah A. Smith from the University of Washington have developed an algorithm even more adept at spotting sarcasm. They say their program recognizes sarcastic text 85% of the time. Sure. Great.
They were able to increase the accuracy thanks to focusing on contextual information and having the huge, free data set that is Twitter, reports Quartz:
The algorithm trains itself to recognize sarcastic posts by scanning tweets with a “#sarcasm” hashtag. Using machine learning, the algorithm gets better at pointing out sarcasm over time. […] Who wrote the tweet was the most important factor — accuracy rose the most when the author’s information was incorporated into the data. But all of the contextual information included in the algorithm — responses, the audience, etc. — made the results more accurate than merely analyzing the text on its own.
Well, la dee da, your majesty.
We’re sure you’ll be so surprised to hear the most sarcastic contingent on Twitter are American males who aren’t verified users. Oh, good for them.