A data layer for measuring public discourse.

Clamor Data turns social video into structured datasets: topic, entity, sentiment, stance and reach, across geography and time. Not just what’s said, but what’s actually seen.

Request a sample dataset Explore datasets

THE ATTENTION GAPMeasured sample

76.5%of views went to just 1% of videos.

Top 1% of videosThe remaining 99%

Counting posts and measuring attention tell different stories.

What the data can reveal

More attention. Growing resistance.

In this fictional example, weekly data-center mentions more than triple over ten months, while sentiment falls and opposition to expansion rises.

Illustrative mockup · fictional data

Data centers / US · EnglishWeekly observations · 03 Nov 2025 – 07 Sep 2026

10-month comparison

Weekly mentions

Videos mentioning data centers

3,840+220%

from 1,200 · 10 months earlier

Average sentiment

Mean score · −1 negative to +1 positive

−0.28−0.40 points

from +0.12 · 10 months earlier

Opposing expansion

Share of mentioning videos · stance

52%+28 pp

from 24% · 10 months earlier

Illustrative sample: 50,000 videos per week (n); 1,200 → 3,840 mention data centers. Sentiment and stance use those mentioning videos. All counts, scores, and dates form a fictional example, not a research finding.

View example weekly values

Fictional weekly data-center observations; 50,000 sampled videos each week.
Week of	Mentions	Sentiment	Opposing
2025-11-03	1,200	0.12	24%
2025-11-10	1,222	0.11	25%
2025-11-17	1,207	0.10	25%
2025-11-24	1,184	0.08	25%
2025-12-01	1,284	0.09	27%
2025-12-08	1,340	0.09	28%
2025-12-15	1,229	0.05	27%
2025-12-22	1,256	0.04	27%
2025-12-29	1,470	0.07	31%
2026-01-05	1,450	0.05	31%
2026-01-12	1,278	-0.01	28%
2026-01-19	1,443	0.01	31%
2026-01-26	1,691	0.05	35%
2026-02-02	1,532	0.00	32%
2026-02-09	1,403	-0.05	30%
2026-02-16	1,723	0.00	35%
2026-02-23	1,889	0.02	37%
2026-03-02	1,618	-0.06	33%
2026-03-09	1,636	-0.08	33%
2026-03-16	2,042	-0.01	39%
2026-03-23	2,044	-0.03	39%
2026-03-30	1,761	-0.12	34%
2026-04-06	1,970	-0.10	37%
2026-04-13	2,341	-0.04	43%
2026-04-20	2,181	-0.10	39%
2026-04-27	2,005	-0.16	36%
2026-05-04	2,358	-0.10	41%
2026-05-11	2,591	-0.08	45%
2026-05-18	2,352	-0.16	40%
2026-05-25	2,354	-0.18	40%
2026-06-01	2,739	-0.12	45%
2026-06-08	2,806	-0.13	46%
2026-06-15	2,609	-0.21	42%
2026-06-22	2,769	-0.20	44%
2026-06-29	3,074	-0.15	48%
2026-07-06	3,037	-0.19	47%
2026-07-13	2,966	-0.24	45%
2026-07-20	3,191	-0.21	48%
2026-07-27	3,371	-0.20	50%
2026-08-03	3,337	-0.24	48%
2026-08-10	3,395	-0.26	48%
2026-08-17	3,578	-0.25	51%
2026-08-24	3,671	-0.26	51%
2026-08-31	3,729	-0.27	51%
2026-09-07	3,840	-0.28	52%

Request a sample 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.

View the full schema

{
  "date": "2026-05-20",
  "region": "US-NY",
  "topic": "housing",
  "entity": "rent",
  "sentiment": -0.42,
  "stance": "negative",
  "share": 0.031,
  "views": 18432,
  "language": "en"
}

Field	Description
date	Observation date (UTC)
region	Geographic region (DMA / country / city)
topic	L1 topic taxonomy
entity	Entity or concept
sentiment	Sentiment score (−1 to 1)
stance	Stance toward the entity
share	Share of total discourse
views	Estimated views for the record
language	Detected language

The catalogue

All datasets

Social Discourse Index

Salience and stance of key topics across regions and time.

Coverage: US, FR, ES, GB, DE, IT, +7
Frequency: Weekly
History: Stated in the sample
Unit: region × topic × week

Explore dataset

Political Narrative

Political entities, issues and narratives at scale.

Coverage: US, GB
Frequency: Daily
History: Stated in the sample
Unit: region × entity × day

Explore dataset

Consumer Intent

Category demand, brand mentions and purchase intent.

Coverage: US, CA, AU, FR, DE, ES
Frequency: Weekly
History: Stated in the sample
Unit: region × brand × week

Explore dataset

Economic Sentiment

Public sentiment around economic and financial topics.

Coverage: US, EU
Frequency: Weekly
History: Stated in the sample
Unit: region × topic × week

Explore dataset

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, with schema, sample sizes and confidence intervals included. Not a brochure.

Request a sample dataset