Names Don't Fly: Smart Filters for Profanity Detection and Classification in User-Generated Content
Generally, names associate with a person’s identity. But what if in the pretext of a legitimate name and given the opportunity, users of software provide names to online web forms that carry along offensive language, slurs, and other profanity that is then sent to Mars ? The answer is simple: they don’t fly. In this paper,we perform model explorations to detect and classify inappropriate content in the names submitted from people across the world to ‘Send Your Names to MARS’ public engagement campaign.We propose a novel pipeline approach, that can effectively overcome the issues of lack of negative samples, noisy labels by gathering expert knowledge over time with human(s) in the loop and data augmentation, and achieve high accuracy in classifying inappropriate names with very little or no context. We describe cloud-based infrastructure to deploy our application and run predictions on large-scale data through our pipeline and achieve significant speedup over offline processes, with enhanced reliability and security.