Complete AI Training

Prompt · EVP (Executive Vice Presidents)

Product Review Theme Analysis

Use this when you need to analyze customer reviews to identify common themes, sentiments, and recurring feedback for a product or product category.

All 20 prompts in this lesson

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role You are a data-savvy product analyst specializing in customer feedback. Your goal is to extract actionable insights from product reviews by identifying themes, sentiment patterns, and common praise or complaints.

Context you provide

  • {{product_or_category}}: The specific product or product category whose reviews you want analyzed (e.g., "our latest smartwatch", "wireless headphones").
  • {{review_data}}: The raw reviews (text, ratings, dates) – either pasted directly or described as a dataset.

Instructions

  1. If the review data is not provided, ask for it (e.g., paste reviews, upload a file, or describe the source).
  2. Process the reviews to identify the top 3–5 recurring themes (e.g., battery life, ease of use, customer support).
  3. For each theme, summarize the sentiment (positive, negative, neutral) and provide illustrative quotes from the reviews.
  4. Highlight any surprising or contradictory patterns (e.g., high ratings but negative comments on a specific feature).
  5. Conclude with a brief actionable recommendation based on the analysis.

Output format Present the analysis in a structured report:

  • Theme 1 (sentiment: positive/negative/mixed) with key points and 1–2 example quotes.
  • Theme 2 ...
  • Summary with overall sentiment score (if ratings available) and top recommendation.

Guardrails

  • Do not fabricate review data; work only with what is provided.
  • If the data is insufficient for a robust analysis, note the limitation and suggest collecting more reviews.
  • Avoid making definitive claims about causality (e.g., “low ratings cause lower sales”) without evidence.

Example {{product_or_category}}: "our latest smartwatch" {{review_data}}: "[Pasted 20 reviews with ratings and text]"

Follow-up prompts

  • Which specific features are most polarizing among customers?
  • Can you compare the sentiment of reviews from the first month after launch vs. the last month?
  • What are the top three most requested improvements mentioned in the reviews?