P

Prompt Gemini for Analyzing User Feedback

Analyzing user feedback is a strategic lever to improve a product, service, or customer experience. However, manually processing hundreds or even thousands of responses takes considerable time and exposes to interpretation bias. Gemini, Google's artificial intelligence model, excels in natural language processing and allows automating this analysis with remarkable accuracy. Thanks to its ability to understand context, detect emotional nuances, and categorize recurring themes, Gemini transforms raw textual data into actionable insights. Whether you manage customer reviews on an e-commerce site, NPS survey responses, social media comments, or support tickets, a well-structured prompt will let you extract key trends, identify priority friction points, and quantify the overall sentiment of your audience. This guide offers an optimized prompt to fully exploit Gemini's analytical capabilities on your user feedback, with variants adapted to each expertise level.

The prompt

Gemini

You are a senior UX analyst specialized in exploiting user feedback. I will provide you with a set of customer feedbacks. Analyze them following this structured methodology:

  1. Sentiment analysis: Classify each feedback as positive, negative, neutral, or mixed. Calculate the distribution in percentages.

  2. Thematic categorization: Identify the 5 to 8 recurring themes (e.g., UX/ergonomics, price, performance, customer support, missing features). For each theme, indicate the number of mentions and the dominant sentiment.

  3. Critical friction points: List the 3 most urgent problems to solve, ranked by frequency and intensity of dissatisfaction. For each, cite a representative verbatim.

  4. Strengths to capitalize on: Identify the 3 most appreciated elements with supporting verbatims.

  5. Weak signals: Spot emerging trends mentioned by few users but potentially important.

  6. Prioritized recommendations: Propose 5 concrete actions ranked by estimated impact (high/medium/low) and implementation effort.

Format your response with tables when relevant. Use emojis for sentiment readability (✅ positive, ❌ negative, ➖ neutral, 🔄 mixed).

Here are the feedbacks to analyze:
[PASTE YOUR FEEDBACKS HERE]

Personalize this prompt with Léa

Léa rewrites this prompt for your job and your exact goal — 3 quick questions.

Why it works

This prompt leverages the role-playing technique by assigning Gemini an expert role, which guides the quality and depth of the analysis. The 6-step methodology structures the model's reasoning sequentially (chain-of-thought), avoiding superficial responses. The explicit request for verbatims, percentages, and tables forces concrete and verifiable outputs rather than generalities.

Expected result

You will obtain a structured analysis report including a quantified overview of sentiment, a thematic mapping of feedback, and a prioritized list of corrective actions. The deliverable is directly usable in product meetings or executive committees, with numerical data and direct quotes that anchor each insight in the real voice of users.

Variants by level

FAQ

How many feedbacks can I analyze at once with Gemini?
Gemini 1.5 Pro has a context window of up to 1 million tokens, allowing you to process several thousand feedbacks in a single request. In practice, for very large volumes (over 2,000 feedbacks), it is recommended to group them by thematic or chronological batches for more precise analysis. For Gemini 1.5 Flash, the window is also very large but analyses will be less nuanced. Remember to structure your feedbacks (one per line, or in CSV format) to facilitate processing.
How should I prepare my feedbacks before submitting them to Gemini for optimal analysis?
The quality of the analysis directly depends on the quality of the input data. Clean your feedbacks by removing exact duplicates, spam, and empty responses. If possible, add contextual metadata like date, source (email, App Store, NPS survey), user segment, or rating. Present them in a structured format: CSV, table, or numbered list. Avoid mixing different languages in the same batch — Gemini handles multilingual, but the analysis will be more consistent if feedbacks are in the same language.
Can Gemini detect sarcasm and cultural nuances in feedback?
Gemini handles explicit sarcasm and common ironic phrases in French (e.g., "Bravo for this update, I love waiting 30 seconds for every click") correctly. However, subtle sarcasm, very local cultural references, or implicit humor can sometimes be misinterpreted. To improve detection, you can add a specific instruction in your prompt: "Be attentive to sarcasm and ironic expressions — when in doubt, flag the feedback as ambiguous rather than misclassifying it." Reviewing feedbacks classified as positive with a low confidence score is a good verification practice.

How to use this prompt

  1. Copy the prompt with the button above.
  2. Paste it into ChatGPT, Claude or your favorite AI assistant.
  3. Replace the bracketed variables with your details, then refine the result.

About Prompt Guide

Prompt Guide is a free library of 4800+ ready-to-use prompts for ChatGPT, Claude and other AIs, with guides to learn prompting and tools to build and optimize your own prompts.

More prompts to explore

Prompt Gemini for Comparing Offers

Comparing commercial offers, whether for a phone subscription, insurance, SaaS software or a B2B supplier, is a time-consuming exercise that requires rigor and method.

Prompt Gemini for Creating a Loyalty Program

Creating an effective loyalty program requires a deep understanding of customer psychology, reward mechanics, and operational constraints

Prompt Gemini for Creating a UI Design

Gemini, Google's artificial intelligence, is emerging as a powerful tool for user interface design. With its multimodal capabilities,

Prompt Gemini for Interview Preparation

Preparing for a job interview is a crucial step that can determine the outcome of your application. Gemini, Google's AI, proves to be a formidable ally.

Prompt Gemini for Optimizing a Landing Page

Optimizing a landing page is a crucial lever for maximizing your conversion rates and making your acquisition campaigns profitable. Gemini, Google's AI model, stands out for its ability to simultaneously analyze textual content, visual structure, and behavioral data of a page. By submitting your landing page to it, you get a comprehensive audit covering message hierarchy, value proposition clarity, call-to-action effectiveness, and user journey consistency. Unlike a manual audit that takes hours, Gemini produces actionable recommendations ranked by potential impact in seconds. Whether you want to reduce your bounce rate, increase sign-ups, or improve your cost per acquisition, the following prompts will help you fully leverage Gemini's analytical capabilities. Each variant is designed for a different expertise level, from beginner marketer to senior growth engineer, so everyone can immediately improve their conversion performance.

Prompt Gemini for Writing a Cover Letter

The cover letter remains a decisive element in any application process. Yet writing a text that captures the recruiter's attention in just a few seconds is a major challenge for many candidates.

Go further

Get new prompts every week

Join our newsletter.