Gemini Prompt for Analyzing Customer Reviews
Customer review analysis has become an indispensable strategic lever for any business looking to improve its products and services. With thousands of reviews scattered across Google, Trustpilot, Amazon, or social networks, manual processing is simply unrealistic. That's where Gemini comes in. Thanks to its advanced natural language understanding capabilities, Gemini can extract sentiment trends, identify recurring pain 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 theme (delivery, product quality, customer service, value for money). Whether you are a marketing manager, product manager, or e-commerce director, using Gemini to analyze your customer reviews allows you to turn raw feedback into concrete business decisions without mobilizing an entire team for weeks.
Paste in your AI
Paste this prompt in ChatGPT, Claude or Gemini and customize the variables in brackets.
You are a specialist analyst 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 distribute 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.
-
Pain 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 5 lines maximum intended for a management committee.
Output format: structure everything into clear sections with tables where relevant. Use emojis for sentiment indicators (🟢 positive, 🟡 neutral, 🔴 negative).
Here are the reviews to analyze:
[PASTE_YOUR_REVIEWS_HERE]
Personalize this prompt with Léa
Answer 3 questions and Léa tailors the prompt to your situation.
Why this prompt works
This prompt leverages a structured 7-dimensional analysis framework that forces Gemini to process reviews comprehensively rather than superficially. Assigning a specialized analyst role 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.
Use Cases
Variants
Expected Output
You will obtain a complete and structured analysis report, comparable to what a customer experience consulting firm would produce. The deliverable includes sentiment distribution and thematic tables, classified customer verbatims, and most importantly, a list of recommendations prioritized by impact and effort. The executive summary allows you to immediately communicate key results to your management.
Frequently Asked Questions
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, theoretically allowing you to analyze several thousand reviews in a single request. In practice, for optimal analysis quality, we recommend processing reviews in batches of 200 to 500. Beyond that, the model may lose precision on fine details. For very large volumes (10,000+ reviews), split them by period, product, or source, then request a cross-synthesis of the partial analyses.
Can Gemini detect fake or manipulated reviews in my analysis?
Gemini can identify certain telltale signs of fake reviews: generic vocabulary not specific to the product, unusually similar phrasing across multiple reviews, an excess of superlatives without concrete details, or suspicious publication patterns. To enable this detection, add an instruction to your prompt like "Identify reviews that seem potentially inauthentic and explain why." However, this detection is 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 within 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 English." Gemini will understand the context and sentiment of each review regardless of its language. For less common languages, accuracy may slightly decrease — in that case, ask Gemini to indicate its confidence level for reviews in those languages.
Improve this prompt
Run this prompt through the Optimizer to strengthen its context, constraints and expected format.
Improve this prompt with the OptimizerComments
- LéaAI
Pour traiter des volumes très élevés d’avis, ajoutez une instruction demandant de ne citer que les 3 avis les plus représentatifs par catégorie, et remplacez les citations longues par des extraits clés. Gagnez en concision sans perdre de lisibilité.
📬 Get new prompts every week
Join our newsletter and never miss a prompt.
Go further
Similar Prompts
Build a recommendation system
Build recommendation systems
Create an automated EDA report
Generate EDA reports automatically
Mistral Prompt for Analyzing Market Trends
Mistral, the leading French AI model, excels at analyzing textual data and synthesizing complex information, making it a particularly well-suited tool for market trend analysis. Whether you are a strategic analyst, entrepreneur, or marketing manager, leveraging Mistral to decipher weak signals, identify underlying shifts, and anticipate changes in your industry gives you a decisive competitive edge. Thanks to its nuanced understanding of French and its ability to process large corpora, Mistral can cross-reference diverse sources—industry reports, economic data, customer feedback, specialized publications—to produce structured and actionable analyses. This guide provides an optimized prompt to turn Mistral into a true trend analyst, capable of spotting emerging patterns, quantifying their potential impact, and formulating strategic recommendations tailored to your context. Learn how to structure your queries to obtain professional-quality market analyses that are reproducible and directly usable in your decision-making processes.
Apply dimensionality reduction
Reduce high-dimensional data