# Google Review Insights: Reputation Reports and Agency Leads (`kodabloomllc/google-review-insights`) Actor

Turns Google Maps reviews into a reputation report per business: rating trend, unanswered bad reviews, owner reply rate, top complaints and 5-star bursts, plus a lead score for agencies.

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

## Pricing

from $10.00 / 1,000 business 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

## Google Review Insights: Reputation Reports and Agency Leads

Turn Google Maps reviews into a one-row reputation report per business. Built for reputation-management and marketing agencies looking for businesses that need help, and for owners who want to see what customers keep complaining about.

### What you get per business

- **Rating trend**: average stars in the recent period (default 90 days) against older reviews: falling, steady or rising
- **Unanswered negative reviews**: 1 and 2 star reviews the owner never replied to, plus the latest one quoted
- **Owner reply rate**: across all reviews and across negative ones, and the median days to reply
- **Top complaints**: rude staff, slow or long wait, late or no-show, overcharged or pricing, quality of work or product, dirty or smell, closed during open hours, billing or refund, communication, injury or safety. Each theme shows how many negative reviews mention it.
- **5-star bursts**: the most 5-star reviews from first-time reviewers (1 or 2 reviews on their profile) within one week
- **Detailed ratings** when Google has them (for example Food, Service, Atmosphere)
- **Reviews per month** and the date of the latest review
- **Lead score** (0 to 100) and a plain-language **summary**

#### Lead score

| Signal | Points |
|---|---|
| Unanswered negative reviews | 8 each, up to 40 |
| Rating falling (recent average 0.4+ stars below older) | 25 |
| Owner replies to under 20% of reviews | 20 |
| 5-star burst of 4+ from first-time reviewers in one week | 15 |

### Example

On the newest 60 reviews of 12 Sacramento businesses (coffee and donut shops, a nail salon, a barber, plumbers):

- **Dunkin' (lead score 65)**: "7 of 17 negative reviews unanswered; rating falling: 3.08 in the last 90 days vs 3.6 before; most common complaint: rude staff"
- **A donut shop and a nail salon (60 each)**: every negative review unanswered (19 of 19 and 25 of 25), owner never replies; top complaints were product quality and rude staff
- **Three 5-star plumbers**: no negative reviews, but bursts of 4 to 7 five-star reviews from first-time reviewers within a week. That is often a business asking customers for reviews, which is allowed; it is shown so you can judge it.

### How to use it

1. Run the **[Google Maps Reviews Scraper](https://apify.com/compass/Google-Maps-Reviews-Scraper)** for the businesses you care about. Sort by **newest** and get at least 50 reviews per place for a good trend reading. You can feed it place URLs or the results of the Google Maps Scraper.
2. Open this actor and pick that run's dataset.
3. Optional: set **Minimum lead score** to 40 to get only businesses worth contacting.

### Output

```json
{
  "name": "Dunkin' Donuts.",
  "category": "Coffee shop",
  "google_rating": 3.5,
  "reviews_analyzed": 60,
  "lead_score": 65,
  "summary": "7 of 17 negative reviews unanswered; rating falling: 3.08 in the last 90 days vs 3.6 before; most common complaint: rude staff",
  "recent_rating": 3.08,
  "older_rating": 3.6,
  "rating_trend": "falling",
  "negative_reviews": 17,
  "unanswered_negative": 7,
  "owner_reply_rate_pct": 55,
  "median_reply_days": 23,
  "top_complaints": "rude staff (6); quality of work or product (3); closed during open hours (1); dirty or smell (1)",
  "five_star_burst": 0,
  "detailed_ratings": "Food 3.71; Service 3.59; Atmosphere 3.63",
  "reviews_per_month": 3.7,
  "latest_unanswered_negative": "...",
  "google_maps_url": "https://www.google.com/maps/..."
}
```

### Good to know

- Complaint themes come from keyword rules checked by hand on real negative reviews, so they catch the common phrasings, not every one.
- The trend needs at least 5 recent and 5 older reviews; otherwise it says "not enough reviews".
- A 5-star burst is a pattern to look at, not proof of fake reviews.
- No reviewer names are needed or output.

### Pricing

You pay per business analyzed, no matter how many reviews it has. Run it with no input to analyze a small built-in demo sample for free.

Made by KodaBloom LLC. Questions: info@kodabloom.com

# Actor input Schema

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

Pick one or more datasets from a Google Maps Reviews Scraper run (compass/Google-Maps-Reviews-Scraper). Sort by newest for the best trend reading.

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

Review objects in the Google Maps Reviews Scraper format.

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

Reviews in this many days count as recent when comparing the rating trend.

## `minLeadScore` (type: `integer`):

Only output businesses with at least this lead score (0 to 100). Every business is still analyzed and counted.

## Actor input object example

```json
{
  "reviews": [],
  "recentDays": 90,
  "minLeadScore": 0
}
```

# Actor output Schema

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

One reputation report per business, best agency leads first.

# 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 = {
    "reviews": []
};

// Run the Actor and wait for it to finish
const run = await client.actor("kodabloomllc/google-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 = { "reviews": [] }

# Run the Actor and wait for it to finish
run = client.actor("kodabloomllc/google-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 '{
  "reviews": []
}' |
apify call kodabloomllc/google-review-insights --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,kodabloomllc/google-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/uDMt6grqrwh6pfh2L/builds/Xo4v5qgf94aQXU66E/openapi.json