AI Review & Feedback Analyzer: Sentiment, Themes & Summary for $1 per 1,000

Turn thousands of reviews, survey answers, support tickets or comments into a clear picture of what customers love, what annoys them and what they ask for. Every item gets sentiment, themes from one consistent taxonomy, feature requests, complaints, praise, urgency, language and a one-line summary. At the end you get one free summary record with theme counts and example quotes, the top complaints, top feature requests and top praise (with real counts), a trend by date and a written executive summary.

It works directly on the output of our Google Play Reviews Scraper and App Store Reviews Scraper, on any other Apify dataset, on a CSV/JSON file, or on text you paste in.

What does the AI Review & Feedback Analyzer do?

• Sentiment per item: positive, neutral or negative, plus a score from -1 to 1. Judged from the text, not just the stars, so a 5-star review that reports a bug is caught.
• Consistent themes: the tool first reads a sample of your data and builds a taxonomy of 5 to 20 themes (for example "Bank Sync", "Pricing & Subscription", "Customer Support"), then tags every item with 1 to 3 of them. Or give it your own category list.
• Feature requests, complaints and praise as short phrases, in the output language you choose.
• Bug flag and urgency (low, medium, high, critical) so data loss, billing errors and crashes rise to the top.
• Language detection for multilingual feedback. Feedback in any language is understood; results are written in English or the language you pick.
• One aggregate record (free): sentiment split, average rating, theme table with example quotes, top complaints / requests / praise grouped by meaning with exact item counts and item IDs, the most urgent items, a trend by day, week or month, and an executive summary with recommendations.

Who uses it?

• App and product teams reading every review after a release instead of skimming a few.
• Customer experience and support leads tagging tickets and survey (NPS/CSAT) comments by theme and urgency.
• Founders and marketers checking what customers praise to use in messaging.
• Agencies and analysts producing review reports for clients or comparing competitors' reviews.

How to use it

1. Get your feedback: run the Google Play Reviews Scraper or App Store Reviews Scraper, export a CSV from your survey or helpdesk tool, or copy the texts.
2. Paste the dataset ID, a file URL, or the texts into the input.
3. Optional: describe what the feedback is about (e.g. "a meditation app"), add your own categories, choose the output language.
4. Click Start. Results appear in the dataset; the last record (recordType: "summary") is the report. It is also saved as SUMMARY in the run's key-value store.

Tip: run it automatically after the review scraper with an Apify integration ("Actor run succeeded" -> start this tool with the scraper's dataset ID), or on a schedule to watch sentiment week by week.

With no input at all the tool analyzes 20 bundled sample reviews of a fictional budgeting app, so you can see the output in about 20 seconds.

Input

Field	Description
datasetId	Apify dataset to analyze (e.g. from our review scrapers or any other Actor)
fileUrls	Links to CSV, JSON, JSON Lines or plain-text files
texts	Pasted feedback, one item per line
textField, titleField, dateField, ratingField, idField	Column/field names. Leave empty to auto-detect common names (text, review, content, comment, date, rating, reviewId...). Dots select nested fields.
passThroughFields	Extra fields copied to each result, e.g. appName, country, appVersion
categories	Your own theme list (optional). Otherwise themes are derived from your data.
maxThemes	Max themes to derive (5-20, default 10)
productContext	A few words on what the feedback is about (improves accuracy)
outputLanguage	Language for summaries and phrases (default English)
maxItems	Analyze at most this many items (0 = all, up to 100,000)
maxTextLength	Long texts are shortened to this many characters (default 1,500)
includeText, includeSummary	Include original text / add the free summary record
anthropicApiKey	Optional: your own Anthropic key for a lower per-item price

Input example

{
  "datasetId": "YOUR_GOOGLE_PLAY_REVIEWS_DATASET_ID",
  "productContext": "a language-learning app",
  "passThroughFields": ["appName", "appVersion"],
  "outputLanguage": "English"
}

Output

Per item (from a real default run)

{
  "recordType": "item",
  "itemId": "s02",
  "sentiment": "negative",
  "sentimentScore": -0.8,
  "themes": ["Bank Sync & Transactions", "App Stability & Bugs"],
  "primaryTheme": "Bank Sync & Transactions",
  "featureRequests": ["Fix bank sync failing almost daily"],
  "complaints": ["Bank sync fails almost every day since update", "Must log out and back in for new transactions"],
  "praise": [],
  "isBugReport": true,
  "urgency": "high",
  "language": "en",
  "summary": "Bank sync fails almost daily since the last update, forcing logouts; user considers churning.",
  "date": "2026-07-06",
  "rating": 2,
  "title": "Sync keeps failing",
  "text": "Bank sync fails almost every day since the last update. I have to log out and back in to see new transactions. Please fix, this is the main reason I pay for it.",
  "textTruncated": false,
  "source": "sample"
}

Summary record (shortened, same run)

{
  "recordType": "summary",
  "itemsAnalyzed": 20,
  "sentimentCounts": {"positive": 9, "neutral": 3, "negative": 8},
  "avgSentimentScore": 0.045,
  "avgRating": 3.1,
  "urgencyCounts": {"low": 10, "medium": 3, "high": 4, "critical": 3},
  "bugReports": 7,
  "themes": [{"theme": "Budgeting & Categories", "count": 6, "share": 0.3, "positive": 4, "neutral": 2, "negative": 0,
              "exampleQuotes": [{"itemId": "s05", "sentiment": "positive", "quote": "The shared household budget is exactly what we needed..."}]}],
  "topComplaints": [{"label": "Bank sync and connection failures", "count": 2, "share": 0.1, "itemIds": ["s02", "s18"],
                     "examples": ["Bank sync fails almost every day since update", "Bank connection drops every few days"]}],
  "topFeatureRequests": [{"label": "Transaction categorization and tagging", "count": 2, "itemIds": ["s06", "s20"]}],
  "topPraise": ["..."],
  "mostUrgent": ["..."],
  "trendGranularity": "month",
  "trend": [{"period": "2026-07", "count": 6, "positive": 3, "neutral": 1, "negative": 2, "negativeShare": 0.333, "avgSentimentScore": 0.117, "avgRating": 3.33, "bugReports": 1}],
  "overallSummary": "Across 20 feedback items, sentiment is mixed and close to neutral (9 positive, 8 negative, 3 neutral; average rating 3.1). Customers consistently praise category breakdowns ... The main problems are app stability and bugs (4 items, all negative) ...",
  "recommendations": ["Prioritize fixing crashes, startup failures, and bank sync connection errors, ..."]
}

Counts in the summary are computed from the per-item results, not estimated by the AI: each complaint, request or praise group lists the exact item IDs it covers.

Pricing

Pay per item analyzed; the summary record is free.

• $1.00 per 1,000 items with our AI (no account or key needed).
• $0.30 per 1,000 items with your own Anthropic API key (Anthropic then bills you directly, typically $0.10-0.25 per 1,000 items).
• Volume discounts on higher Apify plans.

Worked examples: 1,000 Google Play reviews = $1.00. A 10,000-response survey = $10.00. A weekly run on 500 new reviews = $0.50 a week. Items that fail are not charged, and the tool stops at your "maximum cost per run".

Notes and limits

• Texts longer than maxTextLength (default 1,500 characters) are shortened before analysis; textTruncated shows when that happened.
• AI output can occasionally be wrong on sarcasm, very short texts ("ok") or mixed reviews. Spot-check before acting on single items; the aggregate is robust.
• Themes are derived per run. For comparisons across runs (e.g. weekly reports), pass the same categories every time.
• Speed: about 1,000 items in under 2 minutes.

FAQ

Is it legal? The tool only analyzes text you provide or already hold in your Apify account. You are responsible for having the right to process that data (e.g. your own customers' feedback, or public reviews) and for following privacy law such as GDPR when texts contain personal data.

Which AI model does it use? Anthropic Claude (Haiku). Your data is sent to Anthropic's API for processing only.

Can I use it via API? Yes. Start it with the Apify API or client libraries and read the dataset; the summary is also in the key-value store under SUMMARY.

Does it work with Make, Zapier or n8n? Yes, through the Apify integrations for each platform, for example "new survey responses -> analyze -> post summary to Slack".

Can AI agents use it? Yes, through the Apify MCP server, so assistants like Claude can analyze feedback on request.

What about other review sources? Any Apify dataset works. Pick the text field if it is not named text, review, content or comment.

Related tools from Plot Point Technologies

• Google Play Reviews Scraper: Android app reviews to analyze with this tool.
• App Store Reviews Scraper: iOS app reviews with the same field names.
• App Store & Google Play Scraper: app details, search and charts for competitor lists.
• Hacker News Scraper: developer discussions and comments to analyze.
• Website to Markdown Crawler: turn web pages into text for AI pipelines.

Plot Point Technologies is not affiliated with Anthropic, Google or Apple.

If this tool helps you, please leave a review. Found a problem or need a field? Open an issue on the Issues tab and we will look at it quickly.