# AI Review Insights – Sentiment, Pros & Cons, Feature Requests (`ener90/ai-review-insights`) Actor

Turn reviews into AI insights (Gemini or OpenAI, your own key): sentiment per review, top pros & cons, themes, feature requests and a summary per product, in any language. Works with any Apify review dataset (G2, Trustpilot, Walmart, Amazon, Mercado Libre) or JSON.

- **URL**: https://apify.com/ener90/ai-review-insights.md
- **Developed by:** [René Del Valle Rodríguez](https://apify.com/ener90) (community)
- **Categories:** AI, Automation, E-commerce
- **Stats:** 2 total users, 1 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

Pay per event

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

## AI Review Insights – Sentiment, Pros & Cons, Feature Requests

Scraping reviews is easy. Reading 2,000 of them isn't. Point this Actor at a dataset of reviews (from my scrapers, someone else's, or your own JSON) and it gives you sentiment per review plus one summary per product: top pros and cons with how often they come up, themes, feature requests and real quotes. It runs on your own Gemini or OpenAI key.

If you'd rather see it in action first, I recorded a short video tutorial:

https://www.youtube.com/watch?v=qcq8EpkQuYU

![Input form with a dataset of Walmart reviews](https://raw.githubusercontent.com/ENER90/ai-review-insights/main/docs/screenshots/01-input.png)

### What you get

**One `productInsight` row per product.** This real example comes from 100 Walmart reviews, with **Output language** set to Spanish:

| Field | Example |
|---|---|
| `product`, `reviewsAnalyzed`, `averageRating5` | ASUS Chromebook CX15…, `100`, `3.68` |
| `sentiment` | `{"positivePct": 62, "neutralPct": 7, "negativePct": 31, "avgScore": 0.29}` |
| `pros` | \[{"point": "Excelente relación calidad-precio y precio económico", "mentions": 24}, …] |
| `cons` | \[{"point": "Problemas de durabilidad y fallas tempranas", "mentions": 8}, …] |
| `themes`, `featureRequests` | \[{"theme": "Precio y valor", "sentiment": "positive", "mentions": 24}, …] |
| `notableQuotes` | \["Great laptop for the price! It works well, is easy to use…", …] |
| `summary` | A short paragraph you can paste into a report |

**One `reviewSentiment` row per review** (with **Output sentiment per review** on): `product`, `reviewId`, `rating`, `sentiment`, `score` (-1 to 1), `topics` and the review `text`.

![Per-review sentiment from a real run](https://raw.githubusercontent.com/ENER90/ai-review-insights/main/docs/screenshots/02-output-table.png)

### How much it costs

Two parts:

- **Apify:** there's no per-result fee right now. You only pay the platform usage of the run. In my tests, 200 reviews used about $0.006 of Apify credit, so the free $5 monthly plan covers a lot of runs.
- **Your AI provider:** you pay them directly at their price, because the key is yours. Gemini's free tier covers small runs. The default models (`gemini-3.1-flash-lite` or `gpt-4.1-mini`) are the cheap, fast ones.

### How to use it

1. Run any review scraper first, like [Walmart Reviews](https://apify.com/ener90/walmart-products-reviews) or [TrustRadius Reviews](https://apify.com/ener90/software-reviews-scraper), and note its dataset.
2. Open this Actor and pick that dataset in **Apify dataset IDs with reviews**. You can also paste public **JSON URLs**, or paste reviews straight into **Reviews (inline)**.
3. Choose **AI provider** and paste your key in **Your AI API key**. A free Gemini key takes a minute at aistudio.google.com/apikey.
4. Set **Output language** (English, Spanish, Portuguese…). It doesn't need to match the language of the reviews.
5. Click **Start**. Product insights and per-review rows show up in the **Output** tab.

### Input example

```json
{
  "datasetIds": ["vocdGQlze4PYPNQ1A"],
  "llmProvider": "gemini",
  "outputLanguage": "Spanish",
  "groupBy": "product",
  "perReviewSentiment": true,
  "maxReviewsPerProduct": 100
}
```

### Output example (product insight)

![A product insight as JSON](https://raw.githubusercontent.com/ENER90/ai-review-insights/main/docs/screenshots/03-output-json.png)

### Works with

It reads the common review fields automatically (`text`, `rating`, `productName`/`product`), so it works with datasets from my scrapers (Walmart, TrustRadius, Mercado Libre) and from other review scrapers in the Store, like Trustpilot, G2, Capterra, Amazon and Google Maps. Set **Group insights by** to `none` for one summary across everything.

### Use cases

- A one-page "what customers think" report per product or competitor.
- Finding the top 5 complaints and feature requests across hundreds of reviews.
- Tagging every review with sentiment and topics for a dashboard.

### Integrations

- Chain it after a scraper with an Apify **webhook** or in **Make, Zapier or n8n**: run the scraper, then run this Actor with its dataset ID.
- **API:**

```python
from apify_client import ApifyClient
client = ApifyClient("YOUR_TOKEN")
run = client.actor("ener90/ai-review-insights").call(run_input={"datasetIds": ["YOUR_DATASET_ID"], "apiKey": "YOUR_GEMINI_KEY"})
for row in client.dataset(run["defaultDatasetId"]).iterate_items():
    if row["type"] == "productInsight":
        print(row["product"], row["sentiment"])
```

- **AI agents:** add it to [Apify MCP](https://mcp.apify.com).

### Limits

- Free-tier AI keys have per-minute limits. The Actor sends about 30 reviews per request (**Reviews per AI request**) and retries 429 errors with back-off, so big runs just take longer. Keep **Parallel AI requests** at 1–2 on free keys.
- **Max reviews per product** (500) and **Max reviews in total** (2,000) cap how much gets sent to the AI.

### FAQ

**Where does my data go?** Only to the AI provider you choose, with your key. The key is a secret input, stored encrypted and never written to the output or logs.

**Can I analyze Spanish reviews and get English insights?** Yes, set **Output language**.

**Is it legal?** The Actor only processes data you give it. Make sure you're allowed to use the reviews you analyze.

# Changelog

This Actor's version history is a separate document: https://apify.com/ener90/ai-review-insights/changelog.md

# Actor input Schema

## `datasetIds` (type: `array`):

IDs of datasets produced by any review scraper (Trustpilot, G2, Capterra, TrustRadius, Walmart, Amazon, Google Maps, Mercado Libre...). Rows without review text (e.g. product rows) are skipped automatically.

## `jsonUrls` (type: `array`):

Public URLs returning a JSON array of reviews (e.g. an Apify dataset items URL).

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

Reviews as strings or objects with `text` (and optional `productName`, `rating`).

## `llmProvider` (type: `string`):

Which AI provider to use with your own API key.

## `apiKey` (type: `string`):

Your Gemini key (free at https://aistudio.google.com/apikey) or OpenAI key. It is stored encrypted and only used for this run. AI usage is billed by your provider, not by this actor.

## `model` (type: `string`):

Leave empty for a fast, cheap default: gemini-3.1-flash-lite or gpt-4.1-mini.

## `outputLanguage` (type: `string`):

Language for summaries, pros/cons and themes (e.g. English, Spanish, Portuguese, German). Reviews can be in any language.

## `groupBy` (type: `string`):

One insight per product, or one for all reviews together.

## `perReviewSentiment` (type: `boolean`):

Also output one row per review with sentiment, score and topics.

## `maxReviewsPerProduct` (type: `integer`):

Analyze at most this many reviews per product.

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

Analyze at most this many reviews in total.

## `batchSize` (type: `integer`):

How many reviews go in each AI request. Larger = fewer requests.

## `concurrency` (type: `integer`):

Keep 1–2 on free-tier keys to avoid rate limits (429 errors are retried automatically).

## Actor input object example

```json
{
  "datasetIds": [
    "vocdGQlze4PYPNQ1A"
  ],
  "jsonUrls": [],
  "reviews": [
    "Great battery life, but the camera is mediocre.",
    "Shipping took 3 weeks. Please add a dark mode to the app!",
    "Excellent value for money, would buy again."
  ],
  "llmProvider": "gemini",
  "model": "gemini-3.1-flash-lite",
  "outputLanguage": "English",
  "groupBy": "product",
  "perReviewSentiment": true,
  "maxReviewsPerProduct": 500,
  "maxReviews": 2000,
  "batchSize": 30,
  "concurrency": 2
}
```

# Actor output Schema

## `insights` (type: `string`):

No description

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

No description

## `stats` (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 = {
    "jsonUrls": [],
    "reviews": [
        "Great battery life, but the camera is mediocre.",
        "Shipping took 3 weeks. Please add a dark mode to the app!",
        "Excellent value for money, would buy again."
    ],
    "llmProvider": "gemini",
    "outputLanguage": "English",
    "groupBy": "product",
    "perReviewSentiment": true,
    "maxReviewsPerProduct": 500,
    "maxReviews": 2000,
    "batchSize": 30,
    "concurrency": 2
};

// Run the Actor and wait for it to finish
const run = await client.actor("ener90/ai-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 = {
    "jsonUrls": [],
    "reviews": [
        "Great battery life, but the camera is mediocre.",
        "Shipping took 3 weeks. Please add a dark mode to the app!",
        "Excellent value for money, would buy again.",
    ],
    "llmProvider": "gemini",
    "outputLanguage": "English",
    "groupBy": "product",
    "perReviewSentiment": True,
    "maxReviewsPerProduct": 500,
    "maxReviews": 2000,
    "batchSize": 30,
    "concurrency": 2,
}

# Run the Actor and wait for it to finish
run = client.actor("ener90/ai-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 '{
  "jsonUrls": [],
  "reviews": [
    "Great battery life, but the camera is mediocre.",
    "Shipping took 3 weeks. Please add a dark mode to the app!",
    "Excellent value for money, would buy again."
  ],
  "llmProvider": "gemini",
  "outputLanguage": "English",
  "groupBy": "product",
  "perReviewSentiment": true,
  "maxReviewsPerProduct": 500,
  "maxReviews": 2000,
  "batchSize": 30,
  "concurrency": 2
}' |
apify call ener90/ai-review-insights --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,ener90/ai-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/UMbiWhn9y5DaTYlT6/builds/GFeXFNP4XJvXYgHBw/openapi.json