Nostimates

Naver sentiment tracking

naversentimentAnonymous

Naver's blog and cafe corpora are conversational, so sentiment here reflects Korean consumer register rather than reference writing. Classification runs on the Korean text with the evidence sentence retained.

How it renders

Derived from the source-language answer text with evidence retained.

Sampling

Classifications are reported as distributions across n, because the same engine will frame the same brand differently between samples.

Gotcha

Korean politeness levels encode attitude in ways a translated classifier cannot see. Running English classification over translated Korean produces labels that look confident and are not.

What the API returns

A single collection call against Naver for the sentiment field, sampled n times and returned as one object per prompt.

{
  "engine": "naver",
  "field": "sentiment",
  "prompt": "best ai visibility tracking tool",
  "country": "GB",
  "language": "en",
  "n": 30,
  "sentiment": [
    {
      "brand": "Nostimates",
      "label": "recommended",
      "confidence": 0.86,
      "distribution": {
        "recommended": 0.6,
        "neutral": 0.33,
        "hedged": 0.07
      }
    }
  ]
}
GET /v1/collect?engine=naver&field=sentiment

Response fields

KeyTypeNotes
brandstringBrand the classification applies to.
labelstringrecommended | neutral | hedged | negative.
confidencefloatClassifier confidence for this sample.
evidencestringThe sentence the label was drawn from.
distributionobjectLabel shares across the n samples.

What it costs

Add-on field. Priced per collection at a small multiple of the base credit.

See credit pricing →

Naver sentiment FAQ

Which language is classification run in?
Korean, on the original text, with the source sentence returned for audit.
Does politeness level matter?
Considerably. It is part of what the classifier reads.

Get Korean sentiment classified in Korean

Send a Korean prompt set and we will return labels with source-language evidence.

No newsletter. One reply from a human.

Across every engine

Compare how sentiment behaves on every engine we track.

Sentiment across all engines →