Amazon Review Unmet Needs Extractor

Scrape 2-4 star Amazon reviews and identify recurring product gaps, unmet needs, and improvement opportunities. Two analysis modes: AI-powered gap clustering (Groq or OpenAI) or keyword frequency analysis with AFINN sentiment scoring - no AI required.

---

What does Amazon Review Unmet Needs Extractor do?

Amazon Review Unmet Needs Extractor scrapes mixed-rating reviews (2-4 stars) from Amazon product pages and surfaces the patterns that matter for product development. These are the reviews where customers describe exactly what a product is missing.

• Scrape Amazon reviews by star rating - Filter to 2-4 star reviews where buyers describe specific gaps, not just complaints or praise
• AI gap clustering - Groq or OpenAI groups recurring issues into themes with severity, mention count, and representative quotes
• Keyword frequency mode - No AI required. AFINN sentiment scoring labels each frequent phrase as negative (gap), positive (strength), or neutral
• Multiple products per run - Analyze competitor products side by side in a single run
• Works with any Amazon domain - .com, .co.uk, .de, .co.jp, and all other Amazon marketplaces

---

What data can you extract?

AI mode output (one row per identified gap)

Field	Description
gap	One-sentence description of the unmet need
theme	Category label (e.g., "Battery life", "Build quality")
mentionCount	How many reviews mention this gap
mentionPercentage	Percentage of analyzed reviews
severity	high, medium, or low
representativeQuotes	2-3 exact quotes from reviews
starDistribution	Breakdown by star rating

Keyword mode output (one row per frequent phrase)

Field	Description
keyword	Frequent bigram or trigram phrase
frequency	Number of reviews containing this phrase
sentiment	negative, positive, or neutral (AFINN-165)
sentimentScore	Numeric score from -5 to +5
averageStarRating	Average star rating of reviews mentioning this phrase
sentimentContext	Surrounding text snippets for context

---

Why analyze 2-4 star reviews specifically?

5-star reviews are praise. 1-star reviews are frustration. But 2-4 star reviews are where customers describe exactly what would make the product better - specific features they wish existed, quality issues that almost stopped them from recommending, and comparisons to competitors.

Star rating	What reviewers typically say
2 stars	"Almost returned it because..." - Near deal-breakers
3 stars	"Good but..." - Specific feature gaps and tradeoffs
4 stars	"Would be perfect if..." - Minor improvements for next version

---

How does Amazon Review Unmet Needs Extractor work?

1. Parses Amazon product URLs to extract ASINs
2. Scrapes review pages filtered by selected star ratings (default 2-4)
3. Paginates automatically until the review limit is reached (default 50 per product)
4. Analyzes all collected reviews using AI gap clustering or keyword frequency
5. Outputs one row per gap (AI mode) or one row per keyword (frequency mode)

Amazon review pages are server-rendered HTML - no browser needed. Scraping uses Apify residential proxy to avoid blocks.

---

How to use Amazon Review Unmet Needs Extractor?

1. Create an Apify account using your email
2. Open Amazon Review Unmet Needs Extractor in Apify Store
3. Add one or more Amazon product URLs
4. Choose your AI provider (or select None for keyword frequency mode)
5. Click Start and wait for the analysis to complete

---

Input example

Keyword frequency mode (no AI needed)

{
    "productUrls": [
        "https://www.amazon.com/dp/B09XS7JWHH",
        "https://www.amazon.com/dp/B0BX2L8PBT"
    ],
    "starRange": ["2", "3", "4"],
    "maxReviewsPerProduct": 50,
    "aiProvider": "none"
}

AI gap clustering with Groq

{
    "productUrls": [
        "https://www.amazon.com/dp/B09XS7JWHH"
    ],
    "starRange": ["2", "3", "4"],
    "maxReviewsPerProduct": 50,
    "aiProvider": "groq",
    "aiApiKey": "gsk_your_groq_key_here"
}

---

Output example

AI mode

{
    "gap": "Battery drains within 3 hours of moderate use, forcing mid-day recharging",
    "theme": "Battery life",
    "mentionCount": 17,
    "mentionPercentage": 34,
    "severity": "high",
    "representativeQuotes": [
        "Love everything except battery dies by lunch",
        "Would be 5 stars if battery lasted longer"
    ],
    "starDistribution": { "2": 3, "3": 9, "4": 5 },
    "sourceProduct": "Sony WH-1000XM5",
    "sourceAsin": "B09XS7JWHH",
    "totalReviewsAnalyzed": 50,
    "analyzedAt": "2026-04-10T14:30:00.000Z"
}

Keyword mode

{
    "keyword": "battery life",
    "frequency": 17,
    "percentageOfReviews": 34,
    "averageStarRating": 2.8,
    "sentiment": "negative",
    "sentimentScore": -2.3,
    "sentimentContext": [
        "...except battery dies by lunch...",
        "...if battery lasted longer..."
    ],
    "sourceProduct": "Sony WH-1000XM5",
    "sourceAsin": "B09XS7JWHH",
    "totalReviewsAnalyzed": 50,
    "analyzedAt": "2026-04-10T14:30:00.000Z"
}

---

How much does it cost?

Amazon Review Unmet Needs Extractor calls Amazon Reviews Scraper to fetch reviews. The cost of that sub-run is charged to your Apify account in addition to this Actor's compute cost.

• Review scraping: charged per the Amazon Reviews Scraper's pricing model (check its pricing tab for current rates)
• Analysis compute: minimal - keyword mode runs in seconds, LLM mode depends on provider
• AI analysis (optional): Groq free tier handles most runs. OpenAI GPT-4o mini costs ~$0.01 per 50 reviews.

---

Are there other e-commerce tools in Apify Store?

• E-commerce Scraping Tool - Scrape product data, prices, and reviews from any e-commerce site
• Product Matching Vectorizer - Build vector indexes from product catalogs for similarity matching
• E-commerce Product Matching Tool - Match products across competitor catalogs

---

Frequently asked questions

Do I need an AI API key to use Amazon Review Unmet Needs Extractor?

No. Select "None" as the AI provider and Amazon Review Unmet Needs Extractor runs in keyword frequency mode - extracting the most common phrases from reviews and scoring each one with AFINN sentiment analysis. Negative phrases indicate product gaps, positive phrases indicate strengths.

Which AI provider should I use?

Groq offers a free tier that handles most runs. OpenAI GPT-4o mini produces slightly more nuanced gap descriptions but costs ~$0.01 per 50 reviews. Both work well - Groq is recommended for cost-sensitive users.

Can I analyze products from different Amazon domains?

Yes. Amazon Review Unmet Needs Extractor works with any Amazon domain: .com, .co.uk, .de, .co.jp, .fr, .it, .es, and more. Mix domains in the same run to compare regional review patterns.

How are "gaps" different from "negative reviews"?

Gaps are recurring patterns, not individual complaints. A single reviewer saying "the battery is bad" is a review. Seventeen reviewers describing battery drain within 3 hours is a product gap. Amazon Review Unmet Needs Extractor surfaces the patterns, not the noise.

Can I use Amazon Review Unmet Needs Extractor with the Apify API?

Yes. Apify API gives you programmatic access to run Amazon Review Unmet Needs Extractor, manage schedules, fetch results, and integrate with your data pipeline.

Can I use Amazon Review Unmet Needs Extractor through an MCP Server?

Yes. Connect via Apify MCP server for use with Claude Desktop, Claude Code, or any MCP-compatible AI assistant.

Is scraping Amazon reviews legal?

Amazon Review Unmet Needs Extractor only extracts publicly available review data visible to any visitor without login. Read more about the legality of web scraping.

---

Your feedback

Found a bug or have a feature request? Create an issue on the Actor page.