rss
08-03-2016, 10:44 PM
New anti-harassment AI program has 90% success rate
http://i.amz.mshcdn.com/-yUd8eY7uhEE1VgyzTI1AsGYsks=/575x323/https%3A%2F%2Fblueprint-api-production.s3.amazonaws.com%2Fuploads%2Fcard%2Fima ge%2F164374%2FAP51858147.jpghttp://a.amz.mshcdn.com/assets/feed-tw-f7c0a094d16b7ee7c91a1e50839a8e00.jpg (http://twitter.com/share?via=Mashable&text=New+anti-harassment+AI+program+has+90%25+success+rate&url=http%3A%2F%2Fmashable.com%2F2016%2F08%2F03%2Fy ahoo-ai-anti-harassment%2F%3Futm_campaign%3DMash-Prod-RSS-Feedburner-All-Partial%26utm_cid%3DMash-Prod-RSS-Feedburner-All-Partial)http://a.amz.mshcdn.com/assets/feed-fb-c0a21e8841794479b8086c32c6f24ba1.jpg (http://www.facebook.com/sharer.php?u=http%3A%2F%2Fmashable.com%2F2016%2F08 %2F03%2Fyahoo-ai-anti-harassment%2F%3Futm_campaign%3DMash-Prod-RSS-Feedburner-All-Partial%26utm_cid%3DMash-Prod-RSS-Feedburner-All-Partial&src=sp)
Yahoo has developed an AI algorithm that it says can correctly detect up to 90 percent of abusive comments online, making it outperform other "state-of-the-art" deep-learning (https://en.wikipedia.org/wiki/Deep_learning)-based (https://en.wikipedia.org/wiki/Deep_learning) algorithms, according to a report (http://www2016.net/proceedings/proceedings/p145.pdf) by the algorithm's developers.
"While automatically detecting abusive language online is an important topic and task, the prior [abuse detection] has **t been very unified, thus slowing progress ... [abuse] can have a profound impact on the civility of a community or a user’s experience," the developers wrote.
SEE ALSO: Leslie Jones makes triumphant return to Twitter after vanquishing racist trolls (http://mashable.com/2016/07/21/leslie-jones-returns-to-twitter/?utm_campaign=Mash-Prod-RSS-Feedburner-All-Partial&utm_cid=Mash-Prod-RSS-Feedburner-All-Partial) Read more... (http://mashable.com/2016/08/03/yahoo-ai-anti-harassment/?utm_campaign=Mash-Prod-RSS-Feedburner-All-Partial&utm_cid=Mash-Prod-RSS-Feedburner-All-Partial)
More about Instagram (http://mashable.com/category/instagram/?utm_campaign=Mash-Prod-RSS-Feedburner-All-Partial&utm_cid=Mash-Prod-RSS-Feedburner-All-Partial), Twitter (http://mashable.com/category/twitter/?utm_campaign=Mash-Prod-RSS-Feedburner-All-Partial&utm_cid=Mash-Prod-RSS-Feedburner-All-Partial), Harassment (http://mashable.com/category/harassment/?utm_campaign=Mash-Prod-RSS-Feedburner-All-Partial&utm_cid=Mash-Prod-RSS-Feedburner-All-Partial), Artificial Intelligence (http://mashable.com/category/artificial-intelligence/?utm_campaign=Mash-Prod-RSS-Feedburner-All-Partial&utm_cid=Mash-Prod-RSS-Feedburner-All-Partial), and Yahoo (http://mashable.com/category/yahoo/?utm_campaign=Mash-Prod-RSS-Feedburner-All-Partial&utm_cid=Mash-Prod-RSS-Feedburner-All-Partial)http://feeds.feedburner.com/~r/Mashable/~4/km9Tu-ASvwU
http://i.amz.mshcdn.com/-yUd8eY7uhEE1VgyzTI1AsGYsks=/575x323/https%3A%2F%2Fblueprint-api-production.s3.amazonaws.com%2Fuploads%2Fcard%2Fima ge%2F164374%2FAP51858147.jpghttp://a.amz.mshcdn.com/assets/feed-tw-f7c0a094d16b7ee7c91a1e50839a8e00.jpg (http://twitter.com/share?via=Mashable&text=New+anti-harassment+AI+program+has+90%25+success+rate&url=http%3A%2F%2Fmashable.com%2F2016%2F08%2F03%2Fy ahoo-ai-anti-harassment%2F%3Futm_campaign%3DMash-Prod-RSS-Feedburner-All-Partial%26utm_cid%3DMash-Prod-RSS-Feedburner-All-Partial)http://a.amz.mshcdn.com/assets/feed-fb-c0a21e8841794479b8086c32c6f24ba1.jpg (http://www.facebook.com/sharer.php?u=http%3A%2F%2Fmashable.com%2F2016%2F08 %2F03%2Fyahoo-ai-anti-harassment%2F%3Futm_campaign%3DMash-Prod-RSS-Feedburner-All-Partial%26utm_cid%3DMash-Prod-RSS-Feedburner-All-Partial&src=sp)
Yahoo has developed an AI algorithm that it says can correctly detect up to 90 percent of abusive comments online, making it outperform other "state-of-the-art" deep-learning (https://en.wikipedia.org/wiki/Deep_learning)-based (https://en.wikipedia.org/wiki/Deep_learning) algorithms, according to a report (http://www2016.net/proceedings/proceedings/p145.pdf) by the algorithm's developers.
"While automatically detecting abusive language online is an important topic and task, the prior [abuse detection] has **t been very unified, thus slowing progress ... [abuse] can have a profound impact on the civility of a community or a user’s experience," the developers wrote.
SEE ALSO: Leslie Jones makes triumphant return to Twitter after vanquishing racist trolls (http://mashable.com/2016/07/21/leslie-jones-returns-to-twitter/?utm_campaign=Mash-Prod-RSS-Feedburner-All-Partial&utm_cid=Mash-Prod-RSS-Feedburner-All-Partial) Read more... (http://mashable.com/2016/08/03/yahoo-ai-anti-harassment/?utm_campaign=Mash-Prod-RSS-Feedburner-All-Partial&utm_cid=Mash-Prod-RSS-Feedburner-All-Partial)
More about Instagram (http://mashable.com/category/instagram/?utm_campaign=Mash-Prod-RSS-Feedburner-All-Partial&utm_cid=Mash-Prod-RSS-Feedburner-All-Partial), Twitter (http://mashable.com/category/twitter/?utm_campaign=Mash-Prod-RSS-Feedburner-All-Partial&utm_cid=Mash-Prod-RSS-Feedburner-All-Partial), Harassment (http://mashable.com/category/harassment/?utm_campaign=Mash-Prod-RSS-Feedburner-All-Partial&utm_cid=Mash-Prod-RSS-Feedburner-All-Partial), Artificial Intelligence (http://mashable.com/category/artificial-intelligence/?utm_campaign=Mash-Prod-RSS-Feedburner-All-Partial&utm_cid=Mash-Prod-RSS-Feedburner-All-Partial), and Yahoo (http://mashable.com/category/yahoo/?utm_campaign=Mash-Prod-RSS-Feedburner-All-Partial&utm_cid=Mash-Prod-RSS-Feedburner-All-Partial)http://feeds.feedburner.com/~r/Mashable/~4/km9Tu-ASvwU