Sentiment Analysis

Detect toxic language in text using TensorFlow.js Toxicity model

Loading toxicity model...
Lower threshold = more sensitive detection
About

This tool uses Google's Toxicity model to detect toxic language in text. It can identify:

  • Toxic content
  • Severe toxicity
  • Identity attacks
  • Insults
  • Profanity
  • Threats
  • Sexually explicit content