A New Yahoo AI Can Detect Online Abuse, But Automation Isn't the Answer

A New Yahoo AI Can Detect Online Abuse, But Automation Isn’t the Answer

Image: Shutterstock Online harassment is a serious, but tough problem to try and solve. There is a need for a new system that can ease the burden on moderators who have to comb through those reports. As someone who was once responsible for doing that for a local news station (a much smaller venue than, say, Twitter), I can sympathize with the toll seeing all those racist, abusive messages takes on your psyche. It sucks. A team at Yahoo recently developed an algorithm that claims to be able to automatically identify hateful speech. The tool uses deep learning to detect abusive keywords, punctuation that were typically found in hateful comments, and syntactic clues found in several thousand comments on Yahoo’s websites. But that was just the start of it. Researchers…


Link to Full Article: A New Yahoo AI Can Detect Online Abuse, But Automation Isn’t the Answer