Trolls are everywhere online — we even have a few of our own. The problem, until now, has been in correctly identifying what constituted abusive language. As it turns out, even humans are pretty terrible at identifying abuse. Yahoo’s newest algorithm is different. In 90 percent of test cases, it was able to correctly identify an abusive comment — a level of accuracy unmatched by humans, and other state-of-the-art deep learning approaches. The company used a combination of machine learning and crowdsourced suggestions to build the algorithm after trawling the depths of the comment sections at Yahoo News and Finance —…
This story continues at The Next Web
via The Next Web http://ift.tt/2aur4Fq
Comments
Post a Comment