Analyze Sentiment in Customer Feedback
Classify and analyze sentiment in customer reviews, support tickets, or survey responses at scale.
The Prompt
Analyze the sentiment and themes in the following customer feedback. Provide: 1. Overall sentiment distribution (% Positive / Neutral / Negative) 2. Top 5 positive themes with representative quotes 3. Top 5 negative themes with representative quotes 4. Most critical issues (highest frequency + most negative sentiment) 5. Unexpected or surprising feedback 6. Segmentation: if there are patterns by user type, use case, or time period 7. Recommended actions based on findings Feedback to analyze: ``` [PASTE CUSTOMER FEEDBACK, REVIEWS, OR SURVEY RESPONSES] ``` Context: [WHERE THIS FEEDBACK CAME FROM — product reviews, NPS comments, support tickets, etc.]
Example Output
Analyzed 156 pieces of feedback: 62% positive, 23% neutral, 15% negative. Top positive theme: 'Time saved on manual research' (mentioned in 48% of positive responses). Top negative theme: 'Onboarding confusion around API key setup' (appears in 67% of negative responses with high urgency language).
FAQ
Which AI model is best for Analyze Sentiment in Customer Feedback?
Claude Sonnet 4 — excellent at nuanced sentiment analysis and theme extraction.
How do I use the Analyze Sentiment in Customer Feedback prompt?
Copy the prompt, replace the [BRACKETED] placeholders with your specific information, and paste into your preferred AI assistant (ChatGPT, Claude, Gemini, etc.). Analyzed 156 pieces of feedback: 62% positive, 23% neutral, 15% negative. Top positive theme: 'Time saved on manual research' (mentioned in 48% of positive responses). Top negative theme: 'Onboarding confusion around API key setup' (appears in 67% of negative responses with high urgency language).
Model Recommendation
Claude Sonnet 4 — excellent at nuanced sentiment analysis and theme extraction.