Nostimates

Baidu ERNIE sentiment tracking

baidu_erniesentimentAnonymous

Baidu's AI answers are written in a compact encyclopaedic register, so sentiment is more neutral and more consistent than on the chat-style Chinese engines.

How it renders

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

Sampling

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

Gotcha

Encyclopaedic phrasing masks preference. A brand described first and at greater length is being favoured even when every sentence reads as neutral, so we score prominence alongside polarity.

What the API returns

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

{
  "engine": "baidu_ernie",
  "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=baidu_ernie&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 →

Baidu ERNIE sentiment FAQ

Why is Baidu sentiment so neutral?
Its register is reference-like. Prominence carries more signal than polarity here.
Do you score prominence?
Yes, separately, so neutral-but-favoured is visible.

Read Baidu preference through prominence

Send a prompt set and we will return polarity and prominence together.

No newsletter. One reply from a human.

Across every engine

Compare how sentiment behaves on every engine we track.

Sentiment across all engines →