Save 50% on Marqly yearly — now $48/year. Upgrade →
Analysis & Data #sentiment analysis#customer reviews#NLP#feedback#chatgpt

Customer Review Sentiment Analysis Prompt

Classify reviews by sentiment, extract themes, and surface actionable insights.

Full prompt
Analyze the sentiment of the following [number] customer reviews for [product/service].
Reviews:
[paste reviews]
Return:
1. Sentiment distribution (% positive, neutral, negative)
2. Top 10 positive themes and keywords
3. Top 10 negative themes and keywords
4. Most mentioned features
5. 3-5 actionable recommendations for product or marketing
Use a scale of -5 (very negative) to +5 (very positive) where relevant.

How to use this prompt

Paste anonymized data samples and clearly state the decisions the analysis should inform. Always validate numeric outputs.

  1. Copy the full prompt above.
  2. Replace the bracketed placeholders with your own details.
  3. Paste it into chatgpt, claude, gemini (or your preferred AI tool).
  4. Iterate on the output: add constraints, ask follow-ups, or combine multiple results.

Why this prompt works

It gives the AI a clear role, specific inputs, and an output format. That structure reduces vague responses and gives you a draft you can refine in minutes instead of hours.

Frequently asked questions

How many reviews do I need?

Even 20-30 reviews can reveal themes; larger samples improve confidence.

Can AI detect sarcasm?

Sometimes. Cross-check flagged examples manually, especially for short reviews.