The Rewire API now detects violent content!
With our latest API update, we are giving platforms and communities even more tools for protecting their users. So far, the Rewire API has been able to detect ⚠️ hate 💥 abuse
🤬 profanities and 🔞 sexually explicit content.
Now, the API can also detect 🔪 violent content!
Why detect violent content?
Graphic and explicit descriptions of violence should only be accessible to mature audiences. Threats of violence are not acceptable in any online community. By automatically detecting violent content, the Rewire API removes the need for users to manually report harmful content, offering you a more proactive tool for protecting your community.
What’s special about the Rewire API?
We have trained our model for violent content detection on a wide range of data from different domains, to make sure that it can identify any kind of relevant content. At the same time, we made sure that the model is not overly sensitive, so that it does not swamp you with innocuous or idiomatic content incorrectly labelled as being violent (e.g., “I could murder a hamburger”).
Learn more about the Rewire API here, and sign up for free trial access today!