App Review Intelligence

Store Positioning

Store title: App Review Intelligence

Short description: Analyze supplied app reviews for themes, regressions, release issues, sentiment, and product intelligence without live fetching by default.

SEO title: App Review Intelligence — evidence-backed report and intelligence workflow

SEO description: Analyze supplied app reviews for themes, regressions, release issues, sentiment, and product intelligence without live fetching by default. Use it to turn sources into decision-ready rollups, executive summaries, and evidence-backed recommendations.

Categories: ECOMMERCE, AUTOMATION

Keywords: app, review, intelligence, premium report/intelligence actor

Fixed-Inclusive PPE Pricing

This actor uses pay-per-event pricing. Event prices include Apify platform usage; users are not expected to pay a separate platform-usage pass-through charge for the configured pricing model.

• Tier: R1 — Premium report/intelligence actor
• Primary event: evidence-source-processed at $0.00892 base
• Default max charge: $25.00
• Store discounts: FREE/BRONZE base, SILVER discounted, GOLD deepest approved discount

Event set:

• actor-start: base $0.02000, GOLD $0.01600. App Review Intelligence: charged when actor start is completed. The price includes Apify platform usage; no separate usage pass-through is intended.
• evidence-source-processed: base $0.00892, GOLD $0.00714. App Review Intelligence: charged when evidence source processed is completed. The price includes Apify platform usage; no separate usage pass-through is intended.
• finding-emitted: base $0.00892, GOLD $0.00714. App Review Intelligence: charged when finding emitted is completed. The price includes Apify platform usage; no separate usage pass-through is intended.
• report-section-generated: base $0.03600, GOLD $0.02880. App Review Intelligence: charged when report section generated is completed. The price includes Apify platform usage; no separate usage pass-through is intended.
• executive-report-generated: base $0.25000, GOLD $0.20000. App Review Intelligence: charged when executive report generated is completed. The price includes Apify platform usage; no separate usage pass-through is intended.

Public Task Concepts

• Build an App Review stakeholder brief from source rows
• Prioritize App Review findings with evidence and confidence
• Summarize App Review metrics into recommended actions
• Prepare an App Review source table with uncertainty notes
• Export App Review decision rows for review

Analyze supplied app reviews into themes, release regressions, sentiment trends, issue severity, and concise product recommendations. The actor is fixture-first and local-first: it does not fetch App Store or Google Play pages by default, which keeps default runs deterministic and safe for Apify automated checks.

Use Cases

• Triage recent App Store or Google Play review exports after a release.
• Detect repeated crash, login, sync, search, performance, pricing, and feature-request themes.
• Summarize release-health risk into a 0-100 issue score.
• Produce dataset rows for dashboards plus a Markdown summary for product, support, or QA teams.

Input

Set maxChargeUsd to a finite run budget. It defaults to $10; the actor stops before paid work or withholds uncharged reports when the next event would exceed the cap.

Provide reviews for one app or targets for multiple apps. Each review can include:

• reviewId, appId, appName, platform, country
• rating, title, text, version, reviewedAt

Tiny example:

{
  "reviews": [
    {
      "reviewId": "ios-1002",
      "appId": "com.example.notes",
      "appName": "Example Notes",
      "platform": "ios",
      "rating": 1,
      "title": "Crashes when attaching photos",
      "text": "Since version 4.8.1 the app crashes every time I attach a photo to a note.",
      "version": "4.8.1",
      "reviewedAt": "2026-06-30T09:42:00.000Z"
    }
  ],
  "maxReviews": 100,
  "includeReport": true,
  "allowNetworkFetch": false
}

sourceUrls are recorded as references only. Set allowNetworkFetch to false; this build intentionally fails fast if live fetching is requested.

Output

Each dataset row represents one analyzed app target and includes:

• review counts, average rating, latest review date, and detected versions
• positive, neutral, and negative review counts
• dominant themes with severity and sample review IDs
• regression signals such as "after update" or "since version"
• release issue score, status, recommendation, summary, source type, and warnings

The key-value store can also include:

• APP_REVIEW_INTELLIGENCE_RESULTS.json
• APP_REVIEW_INTELLIGENCE_SUMMARY.json
• APP_REVIEW_INTELLIGENCE_REPORT.md

Example output:

{
  "targetId": "example-notes-ios",
  "appId": "com.example.notes",
  "appName": "Example Notes",
  "platform": "ios",
  "status": "critical",
  "reviewCount": 2,
  "averageRating": 2.5,
  "negativeReviewCount": 1,
  "positiveReviewCount": 1,
  "releaseIssueScore": 66,
  "sentimentTrend": "neutral",
  "regressionSignals": ["broke", "since version"],
  "recommendation": "Prioritize a release-health investigation for crashes before expanding roadmap work.",
  "sourceType": "supplied-reviews",
  "sourceUrl": null,
  "warnings": []
}

Public Task Examples

This actor includes five prepared no-fetch task concepts:

• iOS release regression review triage.
• Android app review theme summary.
• Feature request mining from app reviews.
• Multi-app support escalation review scan.
• Reference URL app review audit.

Limits And Safety

• Defaults use a tiny fixture and should finish well under five minutes.
• Network and private API fetching are disabled by default.
• The actor does not collect sensitive personal data and should be used with public or lawfully exported reviews.
• Recommendations are product-operations guidance, not legal, medical, or financial advice.

Limitations

• This build analyzes supplied review exports and fixture inputs; it does not scrape App Store or Google Play pages directly.
• Theme, sentiment, and regression labels are deterministic heuristics, not LLM-generated customer research.
• Sparse review sets can produce incomplete themes, so use larger exports for launch or support decisions.
• Do not submit private or sensitive review data unless you have the required rights and controls.

Local Development

npm install
npm run build
npm test
rm -rf local-qa
mkdir -p local-qa/key_value_stores/default
cp examples/input.tiny.json local-qa/key_value_stores/default/INPUT.json
CRAWLEE_STORAGE_DIR=./local-qa npm run smoke

Troubleshooting

• Network fetching is intentionally disabled: keep allowNetworkFetch set to false and supply exported reviews or targets.
• No usable reviews were supplied: provide at least one review with text, title, or rating, or use the default fixture input.
• Themes look sparse: lower minThemeMentions or provide a larger review export.
• Too much output: lower maxTargets or maxReviews.

FAQ

Does this scrape App Store or Google Play pages?

No. This build analyzes supplied review exports and default fixtures only. sourceUrls are stored as references and are not fetched.

Does this use an LLM?

No. It uses deterministic local heuristics for themes, sentiment, regression phrases, and release-risk scoring.

Can I run this on private customer reviews?

Only use reviews you are allowed to process. Avoid submitting sensitive personal data unless you have the required rights and data-handling controls.