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.
Learn more
Check the full skill on Prompt Guide to master this technique from A to Z.
View on Prompt Guide📬 Get new prompts every week
Join our newsletter and never miss a prompt.
Similar Prompts
Multichannel marketing data analysis
Complete multichannel marketing performance analysis with ROI calculation, attribution models, and budget optimization.
Choose the right visualization for your data
Guide the choice of optimal chart type based on data, audience, and message to communicate.
Web analytics metrics analysis
Comprehensive web analytics metrics analysis to understand visitor behavior and identify optimization areas.
ChatGPT Prompt for Analyzing a Survey
Survey analysis is a crucial step for transforming raw data into actionable insights. Whether you collected responses via Google Forms, Typeform, or any other tool, ChatGPT can help you identify trends, segment respondents, and draw relevant conclusions in minutes. Where an analyst would spend hours cross-referencing variables and writing a report, AI significantly speeds up the process while maintaining methodological rigor. This prompt is designed to guide ChatGPT through a structured analysis of your survey results: synthesis of quantitative data, interpretation of open-ended responses, identification of significant correlations, and formulation of concrete recommendations. It works equally well for a customer satisfaction survey, a market study, or an internal questionnaire. The proposed approach combines descriptive statistical analysis and thematic qualitative analysis, offering you a complete and nuanced view of your results without requiring advanced data science skills.