# Korean Review Classifier – Complaints, Sentiment & Motive (`leoworks/korean-review-classifier`) Actor

Classify Korean customer reviews (Coupang, Naver Shopping, Naver Place, Olive Young…) into complaint types, sentiment and purchase motive with probabilities. Feed any review scraper's dataset — no scraping, no prompt writing.

- **URL**: https://apify.com/leoworks/korean-review-classifier.md
- **Developed by:** [Leoworks](https://apify.com/leoworks) (community)
- **Categories:** AI, E-commerce
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $0.50 / 1,000 review classifications

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

## Korean Review Classifier – Complaints, Sentiment & Purchase Motive

Turn thousands of Korean customer reviews into numbers you can act on. Feed this Actor the output of **any review scraper** (Coupang, Naver Shopping / Smartstore, Naver Place, Olive Young, Musinsa…) or paste review texts, and get every review labelled with:

- **Complaint types** — delivery, quality/defect, size/fit, price/value, customer service, packaging, no effect, skin trouble, other (multi-label, each with a probability)
- **Sentiment** — positive / neutral / negative
- **Purchase motive** — price/discount, reviews & reputation, brand, gift, repurchase, unknown
- **Your own labels** — up to 10 yes/no criteria in plain English or Korean (e.g. "mentions the smell", "배송 기사 불친절")

No scraping, no prompt writing, no LLM key needed. Labels come with English keys **and Korean names** (e.g. `quality_defect` / `품질·불량`), so the output works for global and Korean teams.

**Use it to:** analyze Korean reviews for a product launch · find why Coupang buyers leave 1-star reviews · compare complaint mix against competitors · monitor sentiment of Naver Place reviews for a store · tag reviews for a dashboard or BI tool · Korean sentiment analysis at scale.

### How to use

1. Run a review scraper (for example a Coupang or Naver review scraper on Apify Store).
2. Open this Actor, pick that run's dataset in **Reviews dataset** — or paste texts in **Review texts**.
3. Run. The review text field is detected automatically (`content`, `text`, `review`, `body`, `reviewText`, …). Set **Text field** if your data uses another name, and **Extra text fields** (e.g. `title`) to include a review headline.

```json
{
  "datasetId": "YOUR_REVIEW_DATASET_ID",
  "extraTextFields": ["title"],
  "idFields": ["reviewId", "productId"],
  "customLabels": ["mentions the smell", "says they will buy again"]
}
```

### Output (one row per review)

```json
{
  "reviewId": "324161665",
  "rating": 1,
  "text": "한 달도 안되어서 고장났습니다…",
  "labels": {
    "complaint": [{ "label": "quality_defect", "labelKo": "품질·불량", "probability": 0.97 }],
    "sentiment": { "label": "negative", "labelKo": "부정", "probability": 0.99, "confidence": 0.98 },
    "motive": { "label": "review_trust", "labelKo": "리뷰·평판", "probability": 0.81, "confidence": 0.7 },
    "custom": [{ "label": "mentions the smell", "probability": 0.02, "matched": false }]
  }
}
```

When no complaint type passes the threshold, `complaint` is `[{ "label": "none", "labelKo": "불만 없음" }]`. Full mode also includes `complaintScores` (the probability of every complaint type). **Minimal mode** returns label keys only.

### Accuracy

Measured on 100 hand-labelled Korean reviews (Coupang, Naver Shopping, Naver Place; 47 with 1–4 stars): **complaint type 88%**, **sentiment 96%**. Probabilities are calibrated — raise **Complaint threshold** for fewer, surer labels. Automated labels can be wrong; check samples before making big decisions.

### Pricing

Pay only for classified reviews — no subscription.

| Event | Price | When |
|---|---|---|
| `review-judged` | $0.0005 | One review classified (complaint types, sentiment, purchase motive and any custom labels). |

**Cost examples**

| Reviews | Cost |
|---|---|
| 100 | $0.05 |
| 1,000 | $0.50 |
| 10,000 | $5.00 |
| 100,000 | $50.00 |

With the free $5 monthly Apify credit you can classify about **10,000 reviews**.

Items without review text are skipped and **not charged**. Reviews that fail after retries are reported with an `error` field and **not charged**. If you set a maximum cost per run, the Actor stops cleanly when it is reached.

### Limits

| Item | Limit |
|---|---|
| Review length | First 4,000 characters are used |
| Custom labels | Up to 10, each up to 200 characters |
| Dataset size | Any — datasets are read in pages of 1,000 |
| Languages | Built and tested for Korean; English reviews also work |
| Speed | About 100 reviews in 5 seconds |
| Data | Only the text, rating and the ID fields you choose are sent for classification; reviewer names are not output |

### FAQ

**Which scrapers work?** Any Apify dataset with a review text field. Tested with Coupang, Naver Shopping and Naver Place review scrapers.

**Does it generate text or summaries?** No. It only assigns labels with probabilities — fast, cheap and consistent.

### Changelog

See the Changelog tab.

# Changelog

This Actor's version history is a separate document: https://apify.com/leoworks/korean-review-classifier/changelog.md

# Actor input Schema

## `datasetId` (type: `string`):

An Apify dataset containing reviews — for example the output of a Coupang, Naver Shopping, Naver Place or Olive Young review scraper. Use this OR “Review texts”.

## `texts` (type: `array`):

Paste review texts directly (one per line). Use this OR “Reviews dataset”.

## `textField` (type: `string`):

Field holding the review text. Leave empty to auto-detect (content, text, review, body, reviewText, …).

## `extraTextFields` (type: `array`):

Fields to prepend to the text (up to 5), e.g. `title` for Coupang review headlines. Leave empty if unsure.

## `idFields` (type: `array`):

Fields copied unchanged from each input item to the output so you can join results back (e.g. reviewId, productId). Leave empty to auto-pick reviewId/id/url.

## `customLabels` (type: `array`):

Up to 10 extra yes/no labels (each up to 200 characters) written in plain language (English or Korean), e.g. “mentions the smell”, “배송 기사 불친절 언급”. Each gets a probability.

## `complaintThreshold` (type: `number`):

Minimum probability (0–1) for a complaint type or custom label to be reported. Raise it for fewer, surer labels.

## `outputMode` (type: `string`):

Minimal mode returns only label keys — smaller and easier to aggregate.

## `maxItems` (type: `integer`):

Classify at most this many reviews (0 = all).

## `maxConcurrency` (type: `integer`):

Reviews classified in parallel.

## `healthCheck` (type: `boolean`):

Internal: fail the run when results look degraded (used by the developer's scheduled checks).

## Actor input object example

```json
{
  "texts": [
    "배송이 일주일이나 걸렸고 박스가 다 찢어져서 왔어요.",
    "항상 쓰던 거라 이번에도 재구매했어요. 할인할 때 사니 좋네요!"
  ],
  "extraTextFields": [],
  "idFields": [],
  "customLabels": [],
  "complaintThreshold": 0.5,
  "outputMode": "full",
  "maxItems": 0,
  "maxConcurrency": 10,
  "healthCheck": false
}
```

# Actor output Schema

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

No description

## `summary` (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 = {
    "texts": [
        "배송이 일주일이나 걸렸고 박스가 다 찢어져서 왔어요.",
        "항상 쓰던 거라 이번에도 재구매했어요. 할인할 때 사니 좋네요!"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("leoworks/korean-review-classifier").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 = { "texts": [
        "배송이 일주일이나 걸렸고 박스가 다 찢어져서 왔어요.",
        "항상 쓰던 거라 이번에도 재구매했어요. 할인할 때 사니 좋네요!",
    ] }

# Run the Actor and wait for it to finish
run = client.actor("leoworks/korean-review-classifier").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 '{
  "texts": [
    "배송이 일주일이나 걸렸고 박스가 다 찢어져서 왔어요.",
    "항상 쓰던 거라 이번에도 재구매했어요. 할인할 때 사니 좋네요!"
  ]
}' |
apify call leoworks/korean-review-classifier --silent --output-dataset

```

## MCP server setup

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

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/iCBUB4szdpeQCI0go/builds/FoN6tpUsb8BliRVAf/openapi.json