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.

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

Output (one row per review)

{
  "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.