Computers are using our tweets to learn about sarcasm
A paper titled Contextualized Sarcasm Detection on Twitter saw researchers draw upon tweets to see if a system could identify sarcasm.
Oh great, computers are being taught what constitutes sarcasm through the medium of Twitter.
Researchers pulled together tweets that featured #sarcasm, before the system analysed those tweets, using words like "clearly", "gasp", "I'm shocked" as indicators as to whether the tweets were sarcastic.
Interestingly, wider contextual clues including the identity of the author and the topic they were tweeting about proved to be more effective in detecting sarcasm than the tweet alone. With these clues in place, the system identified sarcasm 85% of the time, a figure that probably beats some internet commenters.
The paper, Contextualized Sarcasm Detection on Twitter, maintains that "this has important consequences for the study of sarcasm and other speech acts on social media with complex audiences." It could even help AI determine whether a statement is true or false, as well as other applications. We're just waiting for the day in which a computer is shown the episode of Father Ted in which Mrs Doyle learns about sarcasm.