paleshadows writes: An Israeli research team from the Hebrew University of Jerusalem has come up with a computer algorithm to identify when online reviewers of products are being sarcastic. The algorithm, called SASI (Semi-supervised Algorithm for Sarcasm Identification), was shown to recognize sarcasm with a 77% hit rate; the researchers suggest that it might be beneficial to include the results of such an algorithm in reviews' summary and ranking systems. The training of the algorithm was based on 66,000 Amazon product reviews that were categorized by 80 sarcastic patterns, factoring syntactic features like the length of sentences, the number question and exclamation marks, and number of capitalized words. (Examples include: "All the features you want — too bad they don't work!"; "Well, you know what happened. ALMOST NOTHING HAPPENED!!!" and "Silly me, the Kindle and the Sony eBook can't read these protected formats. Great!".) From the reviewed products, those most likely to draw sarcastic reviews were Shure and Sony noise cancellation earphones, Dan Brown's Da Vinci Code, and Amazon's Kindle. The researchers noted that "[t]he simpler a product is, the more sarcastic comments it gets if it fails to fill its single function — i.e. noise blocking/cancelling earphones that fail to block the noise". They further speculate that "one of the strong motivations for the use of sarcasm in online communities is the attempt to 'save' or 'enlighten' the crowds and compensate for undeserved hype". The algorithm and its evaluation are described in detail in this academic paper.