App Reviews Intelligence: App Store & Google Play

App Reviews Intelligence

App Reviews Intelligence scrapes App Store reviews and Google Play reviews into one dataset and builds a ready-to-share AI insight report: sentiment, themes, bugs, feature requests, and competitor analysis or a neutral peer comparison (for example Duolingo vs Babbel).

Use it to see what users praise or complain about, compare apps, and watch ratings over time — without extra accounts or API keys. The AI report is included in the price.

Use cases

• Voice of the customer — collect App Store and Google Play reviews for your app and see the main themes.
• Competitor analysis — put your app next to rivals, or compare two peers side by side.
• Bug and request mining — surface crashes, login issues, and the features people ask for most.
• Sentiment and ratings — track star mix, positive / neutral / negative split, and health-style scores.
• Ongoing monitoring — schedule only new reviews runs so you pay only for fresh feedback.

The input form is prefilled with a Duolingo vs Babbel peer comparison (both stores, a modest review cap) so you can start a sample run immediately. Replace those apps with yours.

---

What you get

• Both stores in one dataset — the same fields for iOS and Android reviews.
• AI insight reports — themes, sentiment, bugs, feature requests, and suggested actions, with charts and statistics.
• Comparison modes — your apps vs competitors, or peer comparison (App A vs App B) with neutral labeling.
• Shareable outputs — the report as HTML (printable), Markdown, and JSON, plus the review dataset for spreadsheets and other tools.
• Monitoring — an only new reviews mode for scheduled runs, and memory across runs so trends get richer over time.

On Google Play, very large runs can hit store rate limits; in that case the run shows a warning and may return partial data. Using Apify Proxy helps for heavy use.

---

What the report contains

A typical AI insight report (report.html, report.md, and report.json) includes:

• Summary — how many reviews were saved, how many were already seen, and how many apps were analyzed.
• Ratings and sentiment — review count, average stars, and positive / neutral / negative split for each app and store.
• Metrics — a health score, 7-day and 30-day rating trends when earlier runs exist, the share of 1–2★ reviews, theme share, and on Google Play developer-reply coverage and timing when replies exist.
• Comparison — owner vs competitor, or peer: who leads on ratings and sentiment, shared complaints, and divergent themes (owner mode also notes capability gaps).
• Insights — prioritized themes (impact, suggested action, and sample quotes), feature requests, bugs and reliability issues, and recommended actions.

---

What data can it extract?

Each dataset item is one review. Typical fields:

Field	Description
store	apple or google
appId	Store-specific id or package name
appName	Resolved app title
country	ISO country code
rating	Star rating (1–5)
title	Review title (common on Apple; often null on Play)
text	Review body
date	ISO 8601 timestamp
version	App version when available
thumbsUp	Helpful votes (Google Play)
developerReply	Developer response text
replyDate	Developer reply timestamp
reviewUrl	Public review or app URL
reviewId	Stable review identifier
appRole	primary, competitor, or peer

Example row:

{
  "store": "google",
  "appId": "com.duolingo",
  "appName": "Duolingo",
  "country": "us",
  "rating": 5,
  "title": null,
  "text": "Great daily practice.",
  "date": "2026-10-01T12:00:00.000Z",
  "version": "6.0.0",
  "thumbsUp": 12,
  "developerReply": null,
  "replyDate": null,
  "reviewUrl": "https://play.google.com/store/apps/details?id=com.duolingo",
  "reviewId": "gp-review-id"
}

---

How to use it

1. Open the Input tab (or call the Actor via API or MCP with the same fields).
2. Set apps — App Store numeric IDs, Google Play package names, or store listing URLs (up to 10). For peer comparison, use compareApps with two or more ids (this overrides apps / competitorApps).
3. Choose stores: Apple only, Google only, or both (default). Set countries; only the first country in the list is used per run.
4. Set maxReviewsPerApp (default 80, max 2000).
5. Set a date window: dateFrom / dateTo (inclusive UTC calendar days, YYYY-MM-DD), or if both are empty use sinceDays (last N UTC days). If you set either boundary date, the absolute range wins over sinceDays.
6. Optional: add competitorApps (up to 5) for owner vs competitor, or use comparisonMode / compareApps for peer mode.
7. For recurring monitoring, turn on onlyNew and run the Actor on a schedule: reviews already collected are skipped.
8. Start the run.

---

How much will it cost?

This Actor uses pay-per-event (PPE) pricing on Apify:

Event	Price	Notes
review	$0.0002 each ($0.20 / 1k)	One charge per unique review saved to the dataset
ai_report	$0.15	Once per run, only when the AI insight report is generated
Actor start	$0.00005	Once per run

No API keys or extra accounts needed: the AI report is included in the price.

Example: the prefilled Duolingo vs Babbel run (two apps, both stores, 80 reviews each) can collect up to 320 reviews — about $0.064 plus $0.15 if the AI report is on.

---

Input (summary)

Field	Role
apps	Apps to scrape (App Store ids, Play packages, or URLs; max 10)
stores	apple, google, or both
countries	ISO codes (first country used per run)
maxReviewsPerApp	Cap per app per store (1–2000, default 80)
sinceDays	Relative filter: last N UTC calendar days (ignored if dateFrom or dateTo is set)
dateFrom / dateTo	Optional inclusive UTC day bounds (YYYY-MM-DD); either side can be omitted
onlyNew	Skip reviews already seen in earlier runs (for recurring monitors)
compareApps	2+ app ids → peer mode (overrides apps / competitorApps)
competitorApps	Up to 5 competitors (with apps in owner vs competitor mode)
comparisonMode	Owner vs competitor (default) or peer
includeAiReport	Generate the AI insight report
useMemory	Remember stats across runs for trend metrics (default on)
memoryStoreName	Name of that memory (default app-reviews-memory)

Date filter order (each review’s date is treated as a UTC calendar day):

1. If either dateFrom or dateTo is set → use that range (missing side is open; inclusive on UTC days).
2. Else if sinceDays is set → relative cutoff.
3. Else → no date filter.

If the dates are invalid, the run stops with a clear error message.

---

Output

Output	Description
Dataset	One row per review (see above).
Report	report.html, report.md, and report.json in the run output, when the AI report is on.
memory-summary.json	Summary of trends across runs, when memory is on.

---

Tips

• onlyNew: on scheduled runs you pay only for new reviews; a run with nothing new adds no rows.
• Memory: keep the same memoryStoreName across runs so trends use more history.

---

Use with AI agents (MCP)

You can run this Actor from Claude, Cursor, ChatGPT, and other assistants that support Model Context Protocol, through Apify’s MCP server.

1. Add https://mcp.apify.com as an MCP server in your client. Sign in with Apify when asked (or authorize with your Apify token).
2. To load only this Actor, use https://mcp.apify.com?tools=kupilux/app-reviews-intelligence.
3. Ask the assistant to run kupilux/app-reviews-intelligence. With the default Apify tools, that is the call-actor tool and the Actor name kupilux/app-reviews-intelligence. If you pinned this Actor in the server URL, it also appears as a dedicated tool named like kupilux--app-reviews-intelligence (the same username--actor-name pattern as other pinned Actors).
4. After the run finishes, read the review dataset and the report files (report.html, report.md, report.json).

Minimal example input:

{
  "apps": ["570060128", "com.duolingo"],
  "compareApps": ["570060128", "com.duolingo", "829587759", "com.babbel.mobile.android.en"],
  "stores": "both",
  "countries": ["us"],
  "maxReviewsPerApp": 80,
  "includeAiReport": true
}

Pricing is the same as a run started from the Store page.

---

FAQ & disclaimer

Is scraping app reviews allowed? Reviews are public on store listings. You are responsible for compliance with Apple and Google terms, privacy law, and your use case. This is not legal advice.

Where do I report issues? Use the Issues tab on the Actor page.