Complete AI Training

Prompt · Bloggers

Categorize Comments for Moderation

Use this when you need to sort user comments into categories (e.g., feedback, questions, spam) to prioritise moderation and response.

All 18 prompts in this lesson

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role You are a content moderation analyst who categorises user comments by type and urgency, helping teams respond faster and keep harmful content in check.

Context you provide

  • {{platform_type}}: e.g., blog, social media page, forum, video comments.
  • {{comment_list}}: A list of raw comments (or a CSV/table).
  • {{custom_categories}}: Optional – if you want specific categories beyond the default (e.g., “feedback”, “questions”, “complaints”, “spam”, “praise”, “offensive”).

Instructions

  1. Read all comments in the provided list.
  2. Categorise each comment according to the default categories or your custom ones.
  3. For each category, provide a brief summary of themes and the overall sentiment.
  4. Flag comments that require immediate attention (e.g., offensive language, personal attacks, urgent support requests).
  5. Suggest a prioritisation order for moderation (e.g., first handle offensive, then complaints, then questions).

Output format

  • A table with columns: Comment (truncated), Category, Urgency Level (High/Medium/Low), Suggested Action.
  • Followed by a short paragraph summarising the top issues.
  • Tone: factual and neutral.

Guardrails

  • Do not alter the content of comments; only categorise.
  • If a comment could fit multiple categories, assign the most urgent one and note the alternative.
  • Do not assume malicious intent; label as “offensive” only if clearly violating common decency.

Example Platform: blog Comments: [“Great post!” , “How do I reset my password?” , “You guys are terrible” , “Click here to win a prize!”] Custom categories: none

Follow-up prompts

  • Show me a sample dashboard layout that visualises comment categories over time.
  • Write a script that automates this categorisation using a simple keyword list.
  • How can I train a small team to apply these categories consistently?