📱 App Review Insights: App Store + Google Play reviews → product decisions

Stop reading reviews one by one. Get the answer in 10 seconds: why do users give you 1 star, which release broke things, and what should you build next?

Paste App Store or Google Play links (yours and your competitors'). The Actor collects the latest reviews and runs statistical analysis. You get a clean HTML report plus structured data.

• ✅ Both stores, many countries, one run
• ✅ What drives 1★ vs 5★: the words and themes that statistically separate angry users from happy ones
• ✅ Rating impact per theme: bugs, pricing, ads, login and more, each ranked by how many stars it costs you
• ✅ Version regression alerts: releases whose ratings dropped significantly (Welch t-test)
• ✅ Emerging issues: complaints that spiked in the last 14 days
• ✅ Feature requests, extracted from phrases like "please add…" and "I wish…"
• ✅ Competitor benchmark: side-by-side complaint rates across apps
• ✅ Optional AI analyst summary and ready-to-post replies to 1–2★ reviews, with your own OpenAI / Gemini / Claude key
• ✅ Only new reviews (onlyNewerThan) for daily or weekly monitoring; older reviews are skipped and not charged
• ✅ No duplicates: Google Play shows the same reviews in every country, so each review is fetched and charged once
• ✅ No reviewer names or personal data collected

---

🚀 Quick start

1. Paste app links into Apps, for example https://apps.apple.com/us/app/.../id1232780281 or com.spotify.music.
2. Optionally add competitors to get a benchmark.
3. Choose countries (us, gb, kr, jp…) and max reviews per app.
4. Click Start, then open the HTML report in the Output tab.

📊 What's in the report

Section	What it tells you
Recommendations	A plain-English to-do list generated from the numbers
Themes: what costs you stars	Share of reviews, average rating and rating impact for each theme, plus a typical complaint
Words that predict 1-2★ / 4-5★	Terms far more common in negative (or positive) reviews, with real examples
Emerging issues	Terms whose frequency jumped in recent low-star reviews (two-proportion z-test)
Versions	Average rating per release, with regressions and improvements flagged
Feature requests	What users ask for, ranked by frequency and helpful votes
Weekly trend + distribution	Rating over time and the 1–5★ split
Benchmark (2+ apps)	Complaint rates per theme across you and your competitors

⬇️ Input example

{
  "apps": [
    "https://apps.apple.com/us/app/notion-notes-tasks-ai/id1232780281",
    "notion.id",
    "com.evernote"
  ],
  "countries": ["us", "gb"],
  "playLanguages": ["en", "de"],
  "maxReviewsPerApp": 1000,
  "onlyNewerThan": "90",
  "recentDays": 14
}

⬆️ Output

• HTML report (key-value store → REPORT)
• Insights JSON (OUTPUT): every metric above, ready for dashboards, Slack alerts and AI agents
• Dataset: one row per review, with rating, title, text, date, version, country, themes, sentiment, a feature-request flag, helpful votes and the developer reply (Google Play)

💵 How much does it cost?

Event	Price
Review analysed	$0.0004 (that is $0.40 per 1,000 reviews)
App report (all the analysis + HTML report)	$0.10 per app

Example: a benchmark of 3 apps × 500 reviews costs $0.90; one app with 5,000 reviews costs $2.10. Duplicate and out-of-range reviews are never charged. AI summaries use your own key, so you pay the vendor directly.

🎯 Who is it for?

• Product managers prioritising the roadmap from real user pain
• Mobile developers and QA catching bad releases before the store rating drops
• ASO and marketing teams finding the words users love, to reuse in store listings and ads
• Agencies and investors running quick competitor due diligence on any app

🔁 Automate it

Schedule the Actor weekly with Apify Schedules. Send OUTPUT to Slack, Google Sheets or your BI tool through Apify integrations, and get alerted when a regression or emerging issue appears.

🧠 Methodology

• Themes: a multilingual keyword taxonomy (EN / KO / JA / ZH / ES / DE). Rating impact = theme share × (theme average − overall average).
• Drivers: the share of 1-2★ vs 4-5★ reviews containing each term, tested with a two-proportion z-test (|z| > 1.96).
• Versions: Welch t-test against the previous version, for versions with at least 8 reviews.
• Emerging issues: a two-proportion z-test on ≤3★ reviews, comparing the recent window with the period before. This needs at least 10 days of review history.
• Chinese, Japanese and Korean text is supported through character bigrams, so no language setup is needed.

🤖 Use it from AI agents (MCP): Claude, Cursor & any MCP client

This Actor works as a ready-made connector for AI assistants. Add one URL and your agent can call it on its own:

https://mcp.apify.com?tools=lsso/app-review-insights

• Claude (claude.ai / Claude Desktop): Settings → Connectors → Add custom connector, paste the URL above, sign in to Apify.
• Cursor / VS Code / any MCP client: add it to your MCP config:

{ "mcpServers": { "app-reviews": { "url": "https://mcp.apify.com?tools=lsso/app-review-insights" } } }

• Claude Code: claude mcp add --transport http app-reviews "https://mcp.apify.com?tools=lsso/app-review-insights"

Sign-in uses Apify OAuth in the browser, so you never paste a token into the config. Then just ask:

"Why do users give Spotify 1 star on the App Store this month?"

"Compare the top complaints for Notion and Obsidian on Google Play."

"Did the latest release of my app (com.example.app) hurt its rating?"

The output includes themes ranked by how many stars they cost, version regressions and feature requests, so the agent gets conclusions instead of 1,000 raw reviews. You pay only for results, same as a normal run.

❓ FAQ

How many reviews can I get? The App Store's public feed provides up to 500 reviews per country and sort order; the Actor merges most recent and most helpful to get up to ~1,000 per country, so add more countries to get more. When Apple's feed is having a bad moment (it sometimes returns empty pages for minutes), the Actor moves on quickly instead of burning your time. Google Play supports up to 20,000 per app and language.

Why do more Google Play countries not give more reviews? Google Play shows the same reviews to every country that shares a language. Use Google Play languages (e.g. en, ko, de) to get different reviews.

Is it legal? The Actor reads publicly available reviews only. It never collects reviewer names or avatars and needs no login.

Popular apps only have a few days of reviews in the sample. Very popular apps receive hundreds of reviews per day. Increase Max reviews per app to get enough history for trends and emerging issues.

Can an AI write the summary? Yes. Add an OpenAI, Gemini or Anthropic key and the Actor writes an executive summary, a fix first list, growth levers and a feature roadmap, grounded in the statistics.

📝 Changelog

• 1.1 (2026-09-24): AI reply drafts for negative reviews; onlyNewerThan for monitoring; Google Play by language with de-duplication; App Store merges two sort orders (~1,000 per country) and skips empty feed pages fast; partial results kept if a page fails; Google Play rating histogram in storeInfo; new pricing ($0.40 per 1,000 reviews + $0.10 per app report).
• 1.0: First release: both stores, themes and rating impact, drivers, version regressions, emerging issues, feature requests, benchmark, HTML report.