/Googles hate speech-detecting AI appears to be racially biased

Googles hate speech-detecting AI appears to be racially biased

AI moderators have been touted as a solution to online abuse

Maskot/GettyImages

Artificially intelligent hate speech detectors show racial biases. While such AIs automate the immense task of filtering abusive or offensive online content, they may inadvertently silence minorities.

Maarten Sap at the University of Washington in the US and his colleagues have found that AIs trained to recognise online hate speech were up to twice as likely to identify tweets as offensive when they were written with African-American English or by people who identify as African American.

This includes Perspective, a tool built by Google’s Counter Abuse Technology …

Original Source