Perspective API

Hive’s complete solution to protect your platform. Mobilizing the world's largest distributed workforce of humans labeling data, we are raising the bar for automated content moderation. We offer both best-in-class models as well as manual moderation, allowing us to provide solutions at scale and outperform contract workforces of business process outsourcers (BPOs). In addition to our best-in-class models, our distributed workforce can meet a variety of manual moderation needs. Whether you want to manually moderate user content or annotate training data at scale, our distributed system and consensus policy provide a level of precision that our competitors cannot.

Custom neural network trained to triage reported content. For years, social networks have relied on users to report abuse, hate speech, and other types of online harms. Reports are sent to moderation teams who review each abuse report individually. Many platforms receive thousands of reports daily, most of which can be closed without taking action. Meanwhile, reports containing time-sensitive content — suicide threats, violence, terrorism, and child abuse — risk going unseen or not being reviewed until it’s too late. There are legal implications as well. The German law known as NetzDG says that platforms must remove reported hate speech and illegal content within 24 hours — or face fines of up to 50 million euros. Similar laws concerning reported content are being introduced in France, Australia, the UK, and across the globe. With Two Hat’s reported content product Predictive Moderation, platforms can train a custom AI model on their moderation team’s consistent decisions.