TelegramTrigger Automate

Automate Telegram interactions by analyzing messages for toxic language using Google Perspective. This workflow triggers manually, evaluates message content, and responds with a warning if profanity is detected, promoting a healthier communication environment.

7/8/2025
5 nodes
Medium
manualmediumtelegramtriggergoogleperspectivetelegramnoopcommunicationbotlogicconditional
Categories:
Communication & MessagingManual TriggeredMedium Workflow
Integrations:
TelegramTriggerGooglePerspectiveTelegramNoOp

Target Audience

This workflow is ideal for:
- Community Managers: To monitor and manage toxic language in group chats.
- Moderators: To ensure a safe environment by automatically responding to inappropriate messages.
- Developers: Who want to integrate automated moderation features into their Telegram bots.
- Organizations: Looking to uphold a positive communication standard in their channels.

Problem Solved

This workflow addresses the issue of toxic language in Telegram chats. By integrating with Google Perspective, it evaluates messages for potential toxicity and responds accordingly, ensuring a healthier communication environment.

Workflow Steps

  • Telegram Trigger: The workflow starts when a message is received in a Telegram chat.
    2. Google Perspective: The content of the message is sent to Google Perspective to analyze its toxicity, focusing on attributes like identity attack, threat, and profanity.
    3. IF Condition: The workflow checks if the profanity score exceeds 0.7. If it does, it proceeds to the next step; otherwise, it ends.
    4. Telegram Response: If the message is deemed toxic, a response is sent to the chat, stating: "I don't tolerate toxic language!", referencing the original message for context.
    5. No Operation (NoOp): If the message is not toxic, the workflow completes without any action.

    • Customization Guide

    Users can customize this workflow by:
    - Adjusting Toxicity Thresholds: Modify the profanity score in the IF condition to be more or less sensitive to toxic language.
    - Changing Response Messages: Edit the text in the Telegram node to provide a different response based on the organization's tone or policy.
    - Adding More Attributes: Include additional attributes from Google Perspective to analyze, such as sexual_explicit or insult, to broaden the moderation scope.
    - Integrating Other Platforms: Connect additional messaging platforms or databases to enhance moderation capabilities across different channels.