# Analyze reviews against your own themes

**Use case:** 

Replace the default themes with your own, each with an optional one-line definition, and every review gets positive, negative or not mentioned for each of them (here, a gym: cleanliness, crowding at peak hours, equipment, membership terms and cancellation). Ideal when the default themes of a business type do not match your questions. The sample uses fictional reviews.

## Input

```json
{
  "reviews": [
    {
      "text": "Spotless changing rooms and the machines are always maintained.",
      "rating": 5,
      "placeName": "Iron Club Gym (sample)",
      "category": "Gym",
      "date": "2026-09-08"
    },
    {
      "text": "Impossible to get a bench after 6 pm, way too many members for the space.",
      "rating": 2,
      "placeName": "Iron Club Gym (sample)",
      "category": "Gym",
      "date": "2026-09-21"
    },
    {
      "text": "Cancelling my membership took four emails and they still charged me two more months.",
      "rating": 1,
      "placeName": "Iron Club Gym (sample)",
      "category": "Gym",
      "date": "2026-09-30"
    },
    {
      "text": "Good equipment, but the showers are often cold.",
      "rating": 3,
      "placeName": "Iron Club Gym (sample)",
      "category": "Gym",
      "date": "2026-08-25"
    },
    {
      "text": "Friendly coaches, fair price, quiet in the morning.",
      "rating": 5,
      "placeName": "Iron Club Gym (sample)",
      "category": "Gym",
      "date": "2026-08-02",
      "reply": "Thanks, keep it up!"
    },
    {
      "text": "Two treadmills broken for a month.",
      "rating": 2,
      "placeName": "Iron Club Gym (sample)",
      "category": "Gym",
      "date": "2026-10-03"
    }
  ],
  "businessType": "auto",
  "themes": [
    "cleanliness",
    "crowding: how crowded it gets at peak hours",
    "equipment",
    "contract: membership terms and cancellation"
  ],
  "maxReviews": 500,
  "maxReviewsPerPlace": 100,
  "includeReviewText": true
}
```

## Output

```json
{
  "placeName": {
    "label": "Business",
    "format": "string"
  },
  "reviewsAnalyzed": {
    "label": "Reviews",
    "format": "integer"
  },
  "averageRating": {
    "label": "Rating",
    "format": "number"
  },
  "negativeShare": {
    "label": "Negative share",
    "format": "number"
  },
  "unansweredComplaints": {
    "label": "Unanswered complaints",
    "format": "integer"
  },
  "summary": {
    "label": "Summary",
    "format": "string"
  }
}
```

## How it works

### 1. Sign up on Apify or log in

The Review Analyzer API — Sentiment, Topics & Complaints Actor is ready to run with the inputs already set for "Analyze reviews against your own themes". [Sign up or log in](https://console.apify.com/create-task-from-example/IBgIY7QXOVoibVnHE) and you'll land in Apify Console with a copy of this exact task.

### 2. Start the "Analyze reviews against your own themes" task

The Review Analyzer API — Sentiment, Topics & Complaints Actor will start running based on the input automatically. You can also change all the input fields, like reviews, business type, and more, to match your specific use case.

### 3. Receive the "Analyze reviews against your own themes" output

Monitor the progress in real time. You will be notified as soon as your dataset is complete and ready for review. Each result includes data such as business, reviews, rating, and more.

### 4. Integrate into your workflow

The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow. You can also [run the "Analyze reviews against your own themes" task via API](https://apify.com/sherwood/review-analyzer.md).

## About this Actor

This example demonstrates how to use [Review Analyzer API — Sentiment, Topics & Complaints](https://apify.com/sherwood/review-analyzer.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/sherwood/review-analyzer.md) to learn more, explore other use cases, and run it yourself.


## How to integrate an Actor?

This Task's input is already configured above. Use it as-is rather than inventing a new one.

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 full API examples (JavaScript, Python, CLI, MCP, OpenAPI), see this Task's Actor page: https://apify.com/sherwood/review-analyzer.md

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`).