# App Review Intelligence (`junipr/app-review-intelligence`) Actor

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

- **URL**: https://apify.com/junipr/app-review-intelligence.md
- **Developed by:** [junipr](https://apify.com/junipr) (community)
- **Categories:** Developer tools
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $6.50 / 1,000 evidence source processeds

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event

## What's an Apify Actor?

Actors are web data automations that power AI and operations. They run on the Apify platform to scrape websites, process data, connect APIs, and automate workflows.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.
Actors are written with capital "A".

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
The best way to integrate Actors is as follows.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For usage examples, see the [API](#api) section below.

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).

# README

## 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:

```json
{
  "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:

```json
{
  "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

```bash
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.

# Actor input Schema

## `reviews` (type: `array`):

Review records to analyze when using a single app target. Each item can include reviewId, appId, appName, platform, country, rating, title, text, version, and reviewedAt.

## `targets` (type: `array`):

Optional multi-target input. Each target can include targetId, appId, appName, platform, sourceUrl, and its own reviews array.

## `sourceUrls` (type: `array`):

Reference URLs for review sources. They are recorded in output but not fetched unless a future network implementation explicitly enables it.

## `maxItems` (type: `integer`):

Alias for Max Targets/Maximum Records used by the Junipr actor baseline. When both are provided, actor-specific limits still apply.

## `maxReviews` (type: `integer`):

Maximum reviews analyzed per target. Default is small enough for Apify automated input checks.

## `maxTargets` (type: `integer`):

Maximum app targets analyzed in one run.

## `minThemeMentions` (type: `integer`):

Minimum mentions required before a theme appears in the dominant theme list.

## `includeReport` (type: `boolean`):

Write JSON and Markdown summary artifacts to the key-value store.

## `maxChargeUsd` (type: `number`):

Hard local spending cap for actor-start, per-item, and report events. The actor stops before work or withholds uncharged output when the next event would exceed this amount.

## `dryRun` (type: `boolean`):

Validate and count supplied review inputs without pushing dataset rows.

## `debug` (type: `boolean`):

Enable verbose logs for local troubleshooting.

## `allowNetworkFetch` (type: `boolean`):

Reserved for future live fetching. Keep false for this fixture-first build; true currently fails fast instead of making network calls.

## Actor input object example

```json
{
  "reviews": [
    {
      "reviewId": "ios-1001",
      "appId": "com.example.notes",
      "appName": "Example Notes",
      "platform": "ios",
      "country": "US",
      "rating": 5,
      "title": "Fast again after the latest release",
      "text": "The new version opens faster and sync finally feels reliable. Offline notes showed up after I reconnected.",
      "version": "4.8.1",
      "reviewedAt": "2026-06-29T14:10:00.000Z"
    },
    {
      "reviewId": "ios-1002",
      "appId": "com.example.notes",
      "appName": "Example Notes",
      "platform": "ios",
      "country": "US",
      "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. This broke my trip planning workflow.",
      "version": "4.8.1",
      "reviewedAt": "2026-06-30T09:42:00.000Z"
    }
  ],
  "targets": [],
  "sourceUrls": [],
  "maxItems": 5,
  "maxReviews": 100,
  "maxTargets": 5,
  "minThemeMentions": 1,
  "includeReport": true,
  "maxChargeUsd": 10,
  "dryRun": false,
  "debug": false,
  "allowNetworkFetch": false
}
```

# Actor output Schema

## `results` (type: `string`):

Per-app review intelligence rows with theme, regression, sentiment, release issue, and recommendation fields.

## `summary` (type: `string`):

Run-level JSON summary artifact.

## `report` (type: `string`):

Human-readable Markdown report.

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {};

// Run the Actor and wait for it to finish
const run = await client.actor("junipr/app-review-intelligence").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {}

# Run the Actor and wait for it to finish
run = client.actor("junipr/app-review-intelligence").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{}' |
apify call junipr/app-review-intelligence --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,junipr/app-review-intelligence"
        }
    }
}

```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/mMMERITN7BZ3jKU5b/builds/LtYV9lLM1r8w9nJ9T/openapi.json