Gemini Prompt for Analyzing Customer Reviews

Customer review analysis has become an essential strategic lever for any business looking to improve its products and services. With thousands of reviews scattered across Google, Trustpilot, Amazon, and social media, manual processing is simply unrealistic. That's where Gemini comes in. With its advanced natural language understanding capabilities, Gemini can extract sentiment trends, identify recurring friction points, and surface actionable insights from massive volumes of reviews in seconds. Unlike simple keyword analysis, Gemini understands context, detects irony, distinguishes nuances between constructive criticism and toxic comments, and can even automatically categorize feedback by topic (delivery, product quality, customer service, value for money). Whether you are a marketing manager, product manager, or e-commerce executive, using Gemini to analyze your customer reviews allows you to transform raw feedback into concrete business decisions without mobilizing an entire team for weeks.

The prompt

Gemini

You are an analyst specialized in customer experience and natural language processing. I will provide you with a list of customer reviews. For each batch of reviews, perform a complete analysis following this structure:

Overall sentiment analysis: assign an average sentiment score (from -1 very negative to +1 very positive) and categorize reviews into 5 categories (very positive, positive, neutral, negative, very negative) with percentages.
Main themes: identify the 5 to 8 most mentioned themes (e.g., product quality, delivery time, after-sales service, value for money, packaging, ease of use). For each theme, indicate the number of mentions and the associated sentiment.
Strengths: list the 3 to 5 most appreciated elements by customers, with representative direct quotes.
Friction points: list the 3 to 5 recurring problems, ranked by frequency and impact on satisfaction, with direct quotes.
Weak signals: identify 2 to 3 emerging trends mentioned by few customers but potentially significant.
Actionable recommendations: propose 5 concrete actions prioritized (high impact / low effort first) to improve customer satisfaction.
Executive summary: synthesis in maximum 5 lines intended for a management committee.

Output format: structure everything in clear sections with tables when relevant. Use emojis for sentiment indicators (🟢 positive, 🟡 neutral, 🔴 negative).

Here are the reviews to analyze:
[PASTE YOUR REVIEWS 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 structured 7-dimensional analysis framework that forces Gemini to process reviews comprehensively rather than superficially. Assigning the role of a specialized analyst activates the model's knowledge in NLP and customer experience, while the request for direct quotes anchors the analysis in real data and avoids hallucinations. The weak signals section pushes the model beyond statistical evidence to detect subtle patterns that even a human analyst might miss.

Expected result

You will obtain a complete and structured analysis report, comparable to what a customer experience consulting firm would produce. The deliverable includes sentiment distribution tables by sentiment and theme, classified customer verbatims, and above all a list of recommendations prioritized by impact and effort. The executive summary allows you to immediately communicate key results to your management.

Variants by level

FAQ

How many customer reviews can I analyze at once with Gemini?

Gemini 1.5 Pro has a context window of up to 1 million tokens, which theoretically allows analyzing several thousand reviews in a single request. In practice, for optimal analysis quality, it is recommended to process reviews in batches of 200 to 500. Beyond that, the model may lose accuracy on fine details. For very large volumes (10,000+ reviews), split by period, product, or source, then request a cross-synthesis of partial analyses.

Can Gemini detect fake or manipulated reviews in my analysis?

Gemini can identify certain characteristic signals of fake reviews: generic vocabulary not specific to the product, unusually similar wording across multiple reviews, excessive superlatives without concrete details, or suspicious posting patterns. To activate this detection, add an instruction to your prompt such as 'Identify reviews that seem potentially non-authentic and explain why.' However, this detection remains indicative and does not replace a specialized review fraud detection tool like Fakespot or ReviewMeta.

How do I analyze customer reviews written in multiple languages with Gemini?

Gemini is natively multilingual and can analyze reviews in French, English, Spanish, German, and many other languages in a single request. Simply specify in your prompt: 'The reviews are written in multiple languages. Analyze them all in their original language but produce the final report in French.' Gemini will understand the context and sentiment of each review regardless of its language. For less common languages, accuracy may decrease slightly — in that case, ask Gemini to indicate its confidence level for reviews in those languages.

How to use this prompt

Copy the prompt with the button above.
Paste it into ChatGPT, Claude or your favorite AI assistant.
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.

Prompt library Learn prompting Prompt builder Prompt optimizer

Already have a prompt?

Paste it into the Optimizer, AI improves it in 5 seconds: role, context, format. Free, no signup.

Open the Optimizer

More prompts to explore

Gemini Prompt for Creating a Course Plan

Creating a structured and pedagogically coherent course plan takes time, a clear vision of learning objectives, and a good knowledge of teaching methods.

Gemini Prompt for Creating a Logo

Gemini, Google's multimodal artificial intelligence, offers remarkable capabilities for logo creation thanks to its advanced understanding of language

Gemini Prompt for Creating YouTube Thumbnails

YouTube thumbnails are the first visual element that captures viewers' attention in their recommendation feed. A striking thumbnail can mul

Gemini Prompt for Writing a Blog Post

Gemini, Google's artificial intelligence model, excels at writing long, structured content thanks to its ability to handle extended contexts and produce fluent text in French. To write an effective blog post, it's not enough to just say "write me an article": a well-constructed prompt must specify the topic, tone, expected structure, target audience, and editorial intent. By providing these elements to Gemini, you get a usable first draft that follows SEO best practices, captures attention from the introduction, and guides the reader to the conclusion. This guide offers one main optimized prompt and three variants tailored to your level of expertise, transforming Gemini into a real writing assistant. Whether you're a beginner blogger looking to publish regularly or an experienced content creator aiming for top rankings, these prompts will save you considerable time while maintaining a high level of quality.

Gemini Prompt for Writing a Business Proposal

Writing a compelling business proposal is a strategic exercise that requires combining a strong argument, clear structure, and personalization.

Gemini Prompt for Writing a Contract

Contract writing requires legal precision, editorial clarity, and adaptation to the specific context of each agreement. Gemini, thanks to

Go further

How to prompt Gemini

The complete guide: techniques, examples and best practices.

Free prompt library

4800+ prompts sorted by category, one-click copy.

Get new prompts every week

Join our newsletter.