Education Platforms Moderation

The moderation problem

Education platforms have to host discussion of history, literature, biology, and social issues that legitimately include slurs in quotation, anatomical terms, and descriptions of violence. Block all of it and you've broken the curriculum; allow all of it and you've failed to protect students from peer harassment.

Why a word list isn't enough

A naive filter flags a student quoting a primary source or discussing a banned book the same way it flags a kid bullying a classmate. It can't read intent, so it punishes academic engagement.

How The Profanity API handles it

Use context `educational` so the engine treats quoting and educational intent as legitimate, with `balanced` mode to escalate to LLM analysis when a flagged term appears without an educational frame — catching peer-to-peer abuse without censoring coursework.

const res = await fetch("https://api.theprofanityapi.com/v1/check", {
  method: "POST",
  headers: {
    "Authorization": "Bearer " + process.env.PROFANITY_API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({ text, context: "educational", mode: "balanced" }),
});

const { flagged, intent, score } = await res.json();