I get it. I don't get it.

This fascinating article from NewScientist points to one of the primary difficulties in artificial intelligence research: getting computers to recognize context clues. Companies want cheaper, faster ways to figure out if they're getting good or bad press.

So Corpora has come up with a program called Sentiment, which uses algorithms to tease out grammatical components, such as nouns, verbs and adjectives, and identify the subjects and objects of verbs. It can even analyse pronouns like “it”, “he” and “her” to work out what words or concepts they are referring to.

Having an understanding of grammatical structure makes it possible to filter out words that are not relevant to the sentiment of the article, Jacobi says. So instead of assuming certain words, such as “unpredictable” or “rubbish”, are positive or negative it allows the structural context to disambiguate them....

What makes this kind of analysis so challenging is that key words in a text often offer no clues as to what sentiment they carry. Some of the toughest challenges to comprehension, such as identifying irony and rhetoric, are likely to remain unsolved for some time.

How do you teach a computer to recognize that "fat chance" and "slim chance" mean the same thing? Perhaps irony is a sort of absolute value function--remember those from Algebra I?--where |-5| = 5. So, in order to help teach computers to recognize sarcasm and other forms of irony, let's slightly modify Josh Greenman's idea, and surround ironic statements with absolute value functions. |The future of artificial intelligence is now.|