Clamor DataRequest access

A data layer for measuring public discourse.

Clamor Data transforms social video into structured datasets across topic, entity, sentiment, stance, geography and time.

Dataset catalogue

Clamor Data dataset catalogue
DatasetCoverageFrequencyLabelsHistory
Social Discourse IndexUS, FR, ES, GB, DE, IT, +7Weeklytopic · entity · stance · sentiment · region12 months
Political NarrativeUS, GBDailyentity · issue · stance · narrative · sentiment18 months
Consumer IntentUS, CA, AU, FR, DE, ESWeeklycategory · intent · sentiment · brand12 months
Economic SentimentUS, EUWeeklytopic · sentiment · intensity · region24 months

Topic salience over time

United States · weekly

  • Housing1.63%
  • Immigration1.21%
  • Inflation0.92%
  • Jobs0.74%
  • Healthcare0.48%
48M+
videos processed
17
languages
12 mo
historical coverage
Weekly / Daily
datasets
API · Parquet · CSV
delivery

Our pipeline

From raw social video to structured variables.

Speech is separated from catalogue audio, transcribed, resolved against a maintained taxonomy and aggregated by region and week. Every stage is measured, and the sample size travels with the record.

  1. Video sources

  2. Transcription

  3. Entity & topic

  4. Stance & sentiment

  5. Region & time

  6. Structured dataset

Sample record

Structured. Labeled. Actionable.

Each record is time-stamped, geo-attributed and labeled across multiple dimensions — the same shape whether it arrives over the API, in a Parquet drop or in a historical backfill.

{
  "date": "2026-05-20",
  "region": "US-NY",
  "topic": "housing",
  "entity": "rent",
  "sentiment": -0.42,
  "stance": "negative",
  "share": 0.031,
  "views": 18432,
  "language": "en"
}
FieldDescription
dateObservation date (UTC)
regionGeographic region (DMA / country / city)
topicL1 topic taxonomy
entityEntity or concept
sentimentSentiment score (−1 to 1)
stanceStance toward the entity
shareShare of total discourse
viewsEstimated views for the record
languageDetected language

The catalogue

All datasets

03

Consumer Intent

Category demand, brand mentions and purchase intent.

Coverage
US, CA, AU, FR, DE, ES
Frequency
Weekly
History
12 months
Unit
region × brand × week
Explore dataset
MarketLanguagesVideos processedHistoryCadence
United Statesen, es21.4M24 monthsDaily
United Kingdomen6.1M18 monthsDaily
Spaines, ca4.8M12 monthsWeekly
Francefr5.2M12 monthsWeekly
Germanyde4.4M12 monthsWeekly
Italyit3.0M12 monthsWeekly

Delivery

REST API

Query by region, topic, entity and date range. Cursor pagination, ISO-8601 timestamps, versioned endpoints and a stable record contract.

Bulk export

Parquet and CSV drops to S3, GCS or Azure on your cadence. Full historical backfill lands with the first delivery.

Custom slices

Bespoke taxonomies, entity lists and regional cuts built against a specific research question, delivered on the same schema.

API reference

Quality assurance

A number is only useful if you know what it is a number of.

Known denominator

Sampling is uniform over the identifier space, so a share is a share of a measurable population rather than of whatever a search returned.

Positive controls

Live records of known state are interleaved with every collection run, which separates 'absent' from 'blocked' instead of silently under-counting.

Sample size on every row

Every aggregate ships with n and a 95% interval. Rows thinner than the stated floor are published as null rather than smoothed.

Human validation

A stratified slice of each release is hand-checked against the transcript, and the agreement rate is published with the release notes.

Request a sample dataset.

Tell us the market and the question. We return a real slice — schema, sample sizes and confidence intervals included — not a brochure.