# AI Review Analyzer: Sentiment & Insights from Review Sites (`asvm/ai-review-analyzer`) Actor

Scrape reviews from any review site and get AI-powered insights: sentiment, pain points, strengths, and recommendations. Works with SiteJabber, TripAdvisor, Booking.com, Yelp, Trustpilot, and more. No API key needed. $0.015 per URL.

- **URL**: https://apify.com/asvm/ai-review-analyzer.md
- **Developed by:** [ASVM Studio](https://apify.com/asvm) (community)
- **Categories:** AI, Lead generation, E-commerce
- **Stats:** 3 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $10.00 / 1,000 review analyses

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.
Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#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

## AI Review Analyzer: Sentiment & Insights from Review Sites

Scrape customer reviews from ANY review website and get AI-powered business intelligence: sentiment analysis, customer pain points, competitive strengths, and strategic recommendations. No CSS selectors, no API keys, no per-site configuration needed.

### ⚡ What It Does

1. **Scrapes** customer reviews from any review page URL you provide
2. **Extracts** every review using AI (author, rating, text, date), adapting to any page layout automatically
3. **Analyzes** all reviews with AI for deep business intelligence: sentiment distribution, recurring themes, customer pain points, competitive strengths, and actionable recommendations
4. **Outputs** structured dataset: raw reviews + comprehensive AI analysis report

No CSS selectors. No site-specific code. The AI adapts to any page structure. When a website changes its design, the AI still works, no maintenance needed.

### 🏆 Why This Actor vs Competitors

| Feature | **AI Review Analyzer** | Other AI Scrapers | Traditional Scrapers |
|---------|----------------------|-------------------|---------------------|
| AI sentiment analysis | Full report with themes, pain points, recommendations | Raw data only | Raw data only |
| Works on any review site | Universal | Universal | Per-site code |
| API key needed | AI tokens included | Bring your own | N/A |
| Adapts to layout changes | AI-powered | AI-powered | Breaks on changes |
| Price per URL | **$0.015** | $0.020-$0.025 | $0.003 (no AI) |
| Custom instructions | Per-run custom prompt | Fixed schema | N/A |
| Competitive intelligence mode | Strategic recommendations | No | No |

Other Actors give you raw review data. This Actor gives you raw data PLUS AI-generated business insights: what customers love, what they hate, and what to do about it. Plus, it costs less.

### 📋 Supported Sites

This Actor works on any page with customer reviews. Here are some popular sites:

| Site | Works out of the box | Needs residential proxy |
|------|:---:|:---:|
| SiteJabber | Yes | |
| Booking.com | Yes | |
| TrustSpot / RaveCapture | Yes | |
| Glassdoor | | Recommended |
| TripAdvisor | | Recommended |
| Yelp | | Recommended |
| ProductHunt | | Recommended |
| Capterra | | Recommended |
| Trustpilot | | Recommended |
| G2 | | Recommended |
| ConsumerAffairs | | Recommended |
| Etsy | | Recommended |
| Other review sites | Yes | For sites with anti-bot protection |

For sites in the "Needs residential proxy" column, enable residential proxy in Apify run settings for best results.

### 📥 Input

| Field | Type | Required | Default | Description |
|-------|------|----------|---------|-------------|
| `startUrls` | array | Yes | localhost example | URLs of review pages |
| `maxReviews` | integer | No | 10 | Max reviews to extract per URL (1-500) |
| `analysisType` | enum | No | `detailed` | `summary`, `detailed`, or `competitive` |
| `customPrompt` | string | No | empty | Extra AI instructions (e.g. "Focus on shipping complaints" or "Output in Indonesian") |

#### Example Input

```json
{
  "startUrls": [
    { "url": "https://www.sitejabber.com/reviews/amazon.com" },
    { "url": "https://www.tripadvisor.com/Restaurant_Review-g294229-d1234567-Reviews-..." }
  ],
  "maxReviews": 10,
  "analysisType": "detailed",
  "customPrompt": "Focus on customer service quality and shipping speed"
}
```

### 📤 Output

#### Review Records (`type: "review"`)

Each individual extracted review with rating, author, text, and date.

#### Analysis Record (`type: "analysis"`)

AI-generated insights per URL:

- `overallSentiment`: positive / neutral / negative
- `averageRating`: computed from extracted ratings
- `sentimentDistribution`: percentage breakdown
- `topThemes`: most mentioned topics with per-theme sentiment
- `customerPainPoints`: top issues customers complain about
- `competitiveStrengths`: what customers praise most
- `keyQuotes`: representative quotes from real reviews
- `recommendations`: actionable business recommendations

**Competitive Intelligence mode** adds:

- `competitiveWeaknesses`: areas competitors could exploit
- `strategicRecommendations`: with priority, impact, timeframe
- `marketingOpportunities`: angles derived from positive reviews
- `improvementActions`: immediate fixes from negative reviews

### 💰 Pricing

**$0.015 per URL analyzed** ($15 per 1,000 URLs). All analysis types included at the same flat price.

| Volume | Cost |
|--------|------|
| 10 URLs | ~$0.15 |
| 100 URLs | ~$1.50 |
| 1,000 URLs | ~$15.00 |

No hidden costs. No API key required. AI tokens included in the price.

### 🎯 Use Cases

- **Business owners**: understand what customers really think across review platforms
- **Marketers**: competitive intelligence on competitors' reviews and reputation
- **Sales teams**: pre-meeting research on prospects and their customers
- **Investors**: due diligence on retail, F\&B, hospitality businesses
- **Agencies**: batch analysis for client reputation reports
- **Product managers**: aggregate user feedback across platforms into actionable insights
- **AI agents**: MCP-compatible for automated review monitoring workflows

### 🔧 Technical

- **Runtime**: Node.js 20 (Apify platform)
- **Crawler**: HTTP-based (got-scraping), fast and cost-efficient
- **AI Model**: Included (Advanced AI, fast, accurate, JSON-structured output)
- **Memory**: 512 MB (default)
- **Timeout**: 300s default

# Actor input Schema

## `startUrls` (type: `array`):

URLs of review pages. Works with SiteJabber, TripAdvisor, Booking.com, Yelp, Trustpilot, Glassdoor, ProductHunt, Capterra, and any page that contains customer reviews.

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

Maximum reviews to extract per URL.

## `analysisType` (type: `string`):

Depth of AI analysis. All modes included at the same flat price.

## `customPrompt` (type: `string`):

Extra instructions for the AI analyst. Example: 'Focus on shipping complaints' or 'Compare with competitor X' or 'Output in Indonesian'. Leave empty for default analysis.

## Actor input object example

```json
{
  "startUrls": [
    {
      "url": "https://www.sitejabber.com/reviews/amazon.com"
    }
  ],
  "maxReviews": 10,
  "analysisType": "detailed",
  "customPrompt": ""
}
```

# Actor output Schema

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

Individual customer reviews extracted from the page, each with author, rating, text, and date. Source: JSON-LD structured data or AI extraction.

# 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("asvm/ai-review-analyzer").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("asvm/ai-review-analyzer").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 asvm/ai-review-analyzer --silent --output-dataset

```

## MCP server setup

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

```

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/do7NkGNDxqKMmXIun/builds/gQeVHgQhVreCYcOCk/openapi.json