Automated Toxic Language Detection and Response in Telegram

This n8n workflow automatically monitors messages in a Telegram chat to detect toxic language and responds accordingly. It starts with a Telegram trigger that activates whenever a new or edited message appears in the chat. The message text is then sent to Google Perspective API, which analyzes the message for attributes like profanity, identity attack, and threats, focusing on the English language. If the profanity score exceeds 0.7, the workflow triggers a reply in Telegram, warning users about toxic language. Otherwise, the workflow terminates without action. This setup is highly useful for moderating online communities, maintaining respectful conversations, and automating chat moderation tasks within Telegram groups.