Nostimates

Customer-built analysis

Google News: sentiment

Analyze collected news titles and snippets in your own application.

Collection target: google_news. This is customer-built analysis, not a computed API response field.

Build this analysis in your application

Classify only the article titles and snippets you received, preserving the article URL and classifier version for review. Do not infer the sentiment of a full article or an AI answer from this limited text.

Customer-built analysis

Nostimates does not return sentiment labels, confidence scores or distributions. Classification uncertainty is separate from collection success.

The google_news target returns googleNews.results and googleNews.topNews. Article fields include title, url, snippet, publisher, position and publishedAt. Publication labels are provider text, such as 2 hours ago, not normalized timestamps. News collections can contain empty lists. Google Search and Google News share a task when requested together, while each target has its own outputs and failedRuns count.

Collected input for your analysis

These are illustrative successful run excerpts, not full result files or calculated metrics. Submit POST /v1/crawl-jobs, track completion, then download the authenticated result. Outputs depend on the target; a chatbot has no news articles or Google position fields.

{
  "runNumber": 1,
  "runTaskId": "53b39f0d-9576-44d6-a796-45dbfbfcdbf3",
  "status": "completed",
  "capturedAt": "2026-10-09T10:01:00.000Z",
  "pageUrl": "https://www.google.com/search?q=example&tbm=nws",
  "googleNews": {
    "results": [
      {
        "position": 1,
        "publishedAt": "2 hours ago",
        "publisher": "Example Publisher",
        "snippet": "Illustrative article summary.",
        "title": "Illustrative article title",
        "url": "https://example.com/article"
      }
    ],
    "topNews": []
  }
}
Illustrative provider output. Empty lists and null fields are valid; inspect failedRuns in the result file.
Full result format and failed-run handling →

Sentiment FAQ

Does the API calculate sentiment?
No. Analyze collected news titles and snippets in your own application. The API supplies collected provider outputs; this analysis belongs in your application.
How should failed or empty collections be handled?
Inspect per-target failedRuns and each successful run identity. Empty sources or null fields are valid output; a missing failed run is not an empty successful answer. A completed job can contain failed collections.

Use collected data to build your own reporting and analysis. Our team arranges API access and follows up with next steps.

Request API accessRead the docs