A research team at Hebrew University in Israel has developed a computer program that can recognize sarcasm with about 77 percent accuracy :
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.
(Via: Neatorama )
Dear Reader,
Can I be direct with you?
War abroad. Socialists on the rise. AI upending human life. Endless uproar online. The modern attention economy doesn’t want readers — it wants users enslaved to the tyranny of the present.
First Things is the antidote: literary excellence, timeless truths, and a fixed point of reference in a culture that has lost its bearings.
But we can’t do it without readers like you.
Our goal: Raise $150,000 by November 1 to sustain First Things in the year ahead.
Your gift anchors readers in the permanent things.
Make your Fall Campaign gift now using the button below.
If you have any questions or would like more information, please contact Giovanni Del Piero, Director of the Editor’s Circle, at gdelpiero@firstthings.com or 212-627-1985.
YOU MIGHT ALSO LIKE
The Church in the Age of Therapy
In 1966, Philip Rieff wrote in The Triumph of the Therapeutic that “Religious man was born to…
Canada’s Deadliest Blind Spot
On September 20, the Daily Mail ran a story with the provocative headline, “Our 83-year-old Christian grandmother…
The Faithful Joy of Dolly Parton and Fulton Sheen
Dolly Parton and Fulton Sheen seem to have had little in common. She favored rhinestones; he wore…
