An online sarcasm detector? Yeah, that's useful.
Israeli researchers have developed an algorithm and machine-learning method for identifying sarcasm in online comments that is accurate about 77 percent of the time.
The researchers at Hebrew University turned to a huge trove of review comments on Amazon.com to refine their method. Understanding sarcasm in real-life conversations can sometimes be tricky, and online chatter can get even more confusing. So it would seem a pretty good rate that the researchers' method is accurate about three out of four times.
From the research paper:
We experimented on a data set of about 66,000 Amazon reviews for various books and products. Using a gold standard in which each sentence was tagged by 3 annotators, we obtained precision of 77% and recall of 83.1% for identifying sarcastic sentences. We found some strong features that characterize sarcastic utterances. However, a combination of more subtle pattern-based features proved more promising in identifying the various facets of sarcasm.
And now, a poll:
Via Popular Science
This is an archived version of the technology blog. For updated coverage, see the current baltTech location: baltimoresun.com/balttech