Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Wading through the staggering amount o f social media content being produced every second to find the nastiest bits is no task for humans alone. Even with the newest deep-learning tools at their disposal, the employees who id entify and review problematic posts can be overwhelmed and often traumatized by what they encounter every day. Gigworking annotators, who analyze and label dat a to help improve machine learning, can be paid pennies per unit worked. In a new Concordia-led paper published in IEEE Technology and Society Magazine, researchers argue that supporting these human workers is essential and requires a constant re-evaluation of the techniques and tools they use to identify toxic content. The authors examine social, policy and technical approaches to automatic toxicit y detection and consider their shortcomings while also proposing potential solut ions. "We want to know how well current moderating techniques, which involve both mach ine learning and human annotators of toxic language, are working," says Ketra Sc hmitt, one of the paper's co-authors and an associate professor with the Centre for Engineering in Society at the Gina Cody School of Engineering and Computer S cience.
NETL
NSTL