# App Review Insights (`lsso/app-review-insights`) Actor

Turn App Store and Google Play reviews into product decisions: what drives 1★ vs 5★, themes that cost you stars, version regressions, emerging issues, feature requests and competitor benchmarks. HTML report + JSON + dataset.

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

## Pricing

from $0.40 / 1,000 review analyzeds

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/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
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.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## 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.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## 📱 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

```json
{
  "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:

```json
{ "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.

# Actor input Schema

## `apps` (type: `array`):

App Store or Google Play URLs, Apple app ids (e.g. 324684580) or Android package names (e.g. com.spotify.music). Add competitors to get a side-by-side benchmark.

## `countries` (type: `array`):

Two-letter store country codes, e.g. us, gb, kr, jp, de. App Store reviews are collected per country (up to ~1,000 each). Google Play shows the same reviews in every country of a language, so for Google Play use *Google Play languages* instead — duplicates are never fetched or charged twice.

## `maxReviewsPerApp` (type: `integer`):

Most recent reviews to analyse per app. Google Play: up to 20,000. App Store: Apple's public feed gives about 1,000 per country (most recent + most helpful). More reviews = longer history and better trend detection.

## `onlyNewerThan` (type: `string`):

A date (`2026-09-01`) or a number of days (`30`). Older reviews are skipped and not charged — ideal for a daily/weekly schedule that only looks at new feedback.

## `language` (type: `string`):

Language code for Google Play reviews, e.g. en, ko, ja, de.

## `playLanguages` (type: `array`):

Collect Google Play reviews in several languages, e.g. `en`, `ko`, `ja`, `de`. Leave empty to use *Google Play language* only.

## `recentDays` (type: `integer`):

Window used to detect rising themes and emerging issues (compared with the period before).

## `includeReviews` (type: `boolean`):

Push each enriched review (rating, text, version, themes, sentiment, feature-request flag) to the dataset. Reviewer names are never collected.

## `aiSummary` (type: `boolean`):

If an API key is provided below, an LLM writes an executive summary, fixes and roadmap from the statistics.

## `openaiApiKey` (type: `string`):

Optional. Used only for the AI summary.

## `geminiApiKey` (type: `string`):

Optional. Used only for the AI summary.

## `anthropicApiKey` (type: `string`):

Optional. Used only for the AI summary.

## `aiModel` (type: `string`):

Optional model override for the summary.

## `replyDrafts` (type: `boolean`):

With your own AI key, write ready-to-post developer replies to the most helpful recent 1–2★ reviews (in each review's language). Returned in OUTPUT → `replyDrafts`.

## `replyDraftCount` (type: `integer`):

Per app.

## `replyTone` (type: `string`):

e.g. `friendly, professional` or `short and casual`.

## `summaryLanguage` (type: `string`):

e.g. English, Korean, Chinese, Japanese.

## Actor input object example

```json
{
  "apps": [
    "https://apps.apple.com/us/app/notion-notes-tasks-ai/id1232780281",
    "notion.id"
  ],
  "countries": [
    "us"
  ],
  "maxReviewsPerApp": 500,
  "language": "en",
  "playLanguages": [],
  "recentDays": 14,
  "includeReviews": true,
  "aiSummary": true,
  "replyDrafts": false,
  "replyDraftCount": 10
}
```

# Actor output Schema

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

No description

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

No description

## `reviews` (type: `string`):

No description

# 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 = {
    "apps": [
        "https://apps.apple.com/us/app/notion-notes-tasks-ai/id1232780281",
        "notion.id"
    ],
    "countries": [
        "us"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("lsso/app-review-insights").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 = {
    "apps": [
        "https://apps.apple.com/us/app/notion-notes-tasks-ai/id1232780281",
        "notion.id",
    ],
    "countries": ["us"],
}

# Run the Actor and wait for it to finish
run = client.actor("lsso/app-review-insights").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 '{
  "apps": [
    "https://apps.apple.com/us/app/notion-notes-tasks-ai/id1232780281",
    "notion.id"
  ],
  "countries": [
    "us"
  ]
}' |
apify call lsso/app-review-insights --silent --output-dataset

```

## MCP server setup

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

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/MpRXZ39xEwVMuFgae/builds/GKjs7P4QIsTqhpQYP/openapi.json