ChatGPT Prompt to Analyze Customer Reviews
Customer review analysis has become a strategic lever for any company looking to improve its products, services, and customer experience. But manually processing hundreds or thousands of Google, Trustpilot, Amazon, or social media reviews is a colossal and time-consuming task. ChatGPT changes the game by allowing you to extract trends, dominant sentiments, and actionable insights from your text data in minutes. With well-crafted prompts, you can automatically categorize feedback by theme (product quality, customer service, delivery, value for money), identify recurring friction points, and spot improvement opportunities that your competitors miss. AI excels particularly in sentiment analysis, verbatim summarization, and pattern detection invisible to the human eye when dealing with large volumes. Whether you are a product manager, CX manager, or e-commerce professional, these prompts will turn your raw customer reviews into an actionable qualitative dashboard for business decisions.
Paste in your AI
Paste this prompt in ChatGPT, Claude or Gemini and customize the variables in brackets.
You are a senior CX (Customer Experience) analyst specialized in verbatim analysis and text mining. I will provide you with a list of customer reviews. Analyze them in depth according to this methodology:
Reviews to analyze:
[PASTE YOUR CUSTOMER REVIEWS HERE - one per line, or as a numbered list]
Required analysis:
-
Overall summary: Summarize the general sentiment in 3-4 sentences. Indicate the approximate positive/neutral/negative distribution.
-
Detailed sentiment analysis: For each review, assign a sentiment score (very positive / positive / neutral / negative / very negative) and identify the dominant emotion (satisfaction, frustration, disappointment, enthusiasm, anger, indifference).
-
Thematic categorization: Classify each review into one or more categories: product quality, customer service, delivery/logistics, value for money, shopping experience, ease of use, design/aesthetics, reliability/durability. If a recurring theme is not in this list, create a new category.
-
Top 5 strengths: The most appreciated elements by customers, with number of mentions and illustrative verbatims.
-
Top 5 friction points: The major irritants, ranked by frequency and impact, with illustrative verbatims.
-
Actionable insights: Propose 5 concrete, prioritized recommendations (quick wins vs. long-term projects) based on the analyzed data. For each recommendation, indicate the expected impact (high/medium/low) and implementation effort.
-
Weak signals: Identify 2-3 emerging trends or minority concerns that could become significant.
Format your response with Markdown tables where relevant. Be factual and support every conclusion with the provided data.
Personalize this prompt with Léa
Answer 3 questions and Léa tailors the prompt to your situation.
Why this prompt works
This prompt leverages role framing (senior CX analyst) to activate a rigorous analytical register rather than a conversational one. The 7-step methodology imposes an exhaustive structure that forces the model to process reviews from multiple complementary angles — sentiment, theme, frequency, impact — avoiding superficial analysis. Requests for illustrative verbatims and prioritization (quick wins vs. long-term) anchor the analysis in real data and ensure directly actionable recommendations.
Use Cases
Variants
Expected Output
You will get a structured analysis report including an overall sentiment summary, a categorization table by theme and sentiment, a ranking of strengths and friction points with verbatims, and 5 prioritized recommendations. The document will be ready to present in a team meeting or to feed your product roadmap and continuous improvement strategy.
Frequently Asked Questions
How many customer reviews can ChatGPT analyze at once?
ChatGPT can process between 50 and 150 short reviews in a single prompt, depending on their length. For larger volumes, the best approach is to split your reviews into batches of 50–100, analyze each batch separately, then ask ChatGPT to consolidate the results into an overall summary. With GPT-4 and its extended context window, you can handle even larger volumes. For very large corpora (1,000+ reviews), consider using the API with a script that automates batch processing.
Is ChatGPT's sentiment analysis reliable compared to specialized tools?
ChatGPT offers remarkable accuracy for sentiment analysis, often comparable to specialized tools like MonkeyLearn or Lexalytics on French-language texts. Its main advantage lies in its ability to understand sarcasm, irony, and contextual nuances better than lexicon-based tools. However, it can lack consistency across very large datasets and does not provide statistically calibrated scores. For rigorous business use, it's recommended to validate ChatGPT's results on a sample of 50 manually annotated reviews in order to gauge its reliability on your specific corpus.
How should I format my customer reviews before submitting them to ChatGPT?
The optimal format is a numbered list with one review per line: "1. [Review] — 2. [Review] — etc." If you have useful metadata (date, star rating, source platform, product concerned), include it in brackets before each review: "1. [4★ - Google - 12/01/2025] Great product but slow delivery..." Avoid complex table formats that consume a lot of tokens. Remove duplicates and spam reviews before submission. If your reviews come from an Excel file, export them as plain text with a clear separator between each entry.
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.