Themes and trends

Two different things

Sigmora keeps stable themes separate from fast-moving trends.

Personal Finance, Beauty, and Video Gaming are themes: durable classifications describing what content is about.
A bank failed this morning or creators are switching to a new editing format are trends: time-bound clusters of observations.

Keeping them apart keeps theme ids stable and lets you compare analytics over time.

The taxonomy

Themes follow the IAB Tech Lab Content Taxonomy 3.1. GET /v1/themes reports the taxonomy version and the SHA-256 of the exact source file in use. A platform’s own category, such as YouTube’s videoCategoryId, is kept as evidence and mapped into the taxonomy. It is not the theme itself: platform categories are regional, platform-specific and broad. The supported values can be retrieved from YouTube videoCategories.list.

curl "https://api.sigmora.org/v1/themes?rootOnly=true" \
  -H "Authorization: Bearer $SIGMORA_API_KEY"

Theme ids are namespaced and versioned, for example:

{
  "id": "iab:3.1:391",
  "name": "Personal Finance",
  "rootId": "iab:3.1:391",
  "path": ["Personal Finance"],
  "taxonomyVersion": "3.1"
}

themeId is a versioned id, not free text. Copy themes[].id exactly as returned. See Identifiers.

Filter to a theme’s children with parentId, to top-level themes with rootOnly=true, or search names with q. Page with cursor and nextCursor (see Pagination).

Classify content

POST /v1/themes/classify assigns themes to a piece of content using the same rules applied when content is collected. It is free.

curl -X POST https://api.sigmora.org/v1/themes/classify \
  -H "Authorization: Bearer $SIGMORA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "title": "Three ways founders can extend their runway",
    "description": "Cash flow and business banking for an early-stage SaaS",
    "hashtags": ["startup", "finance"],
    "sourceCategories": [
      { "system": "youtube-video-category", "id": "27", "label": "Education" }
    ]
  }'

import os
import requests

classification = requests.post(
    "https://api.sigmora.org/v1/themes/classify",
    headers={"Authorization": f"Bearer {os.environ['SIGMORA_API_KEY']}"},
    json={
        "title": "Three ways founders can extend their runway",
        "description": "Cash flow and business banking for an early-stage SaaS",
        "hashtags": ["startup", "finance"],
        "sourceCategories": [{"system": "youtube-video-category", "id": "27", "label": "Education"}],
    },
    timeout=30,
).json()

const classification = await fetch("https://api.sigmora.org/v1/themes/classify", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.SIGMORA_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    title: "Three ways founders can extend their runway",
    description: "Cash flow and business banking for an early-stage SaaS",
    hashtags: ["startup", "finance"],
    sourceCategories: [{ system: "youtube-video-category", id: "27", label: "Education" }],
  }),
}).then((r) => r.json());

Each assignment carries:

canonical themeId and rootThemeId;
confidence;
method (provider-category, keyword-rules, ai, manual, or fallback);
human-readable reasons;
the tagger version and assignment time.

When nothing matches reliably, the result is sigmora:general marked needs-review — never an invented high-confidence category. Collected content can later gain an ai assignment from deeper analysis, and a manual assignment always takes precedence.

Detect a business’s niche

POST /v1/niches/detect turns a description of a business into the same theme ids used for content:

curl -X POST https://api.sigmora.org/v1/niches/detect \
  -H "Authorization: Bearer $SIGMORA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "businessName": "Acme Money",
    "businessDescription": "We teach young professionals about investing and credit scores.",
    "products": ["personal finance course"],
    "audience": "first-time investors"
  }'

A Brand created with a niche or description gets this profile automatically, and it is recomputed when that text changes. It drives discovery, idea ranking and competitor selection. A vague description returns needs-review — let the person correct it during onboarding.

Economics is a prior, not a payout prediction

Theme definitions contain qualitative economics:

monetization tier;
commercial intent;
likely monetization routes;
advertiser categories;
compliance and brand-safety risks.

These are a starting prior, not CPM, RPM, revenue or advertiser-demand forecasts. Actual earnings depend on audience geography, platform, format, season, account eligibility, inventory and measured channel performance. Your observed results override the prior when ranking; they never change the taxonomy. So finance can carry a premium prior and a financial-claims risk without any claim that a finance video will earn a particular amount.

Viral content

Every collected item carries its theme assignment.

curl "https://api.sigmora.org/v1/viral-content?themeId=iab%3A3.1%3A391&minScore=70" \
  -H "Authorization: Bearer $SIGMORA_API_KEY"

Each item includes the platform’s original categories and a themes object with the primary theme, its ancestors, how it was assigned, and the theme’s economics.

Trend signals

curl "https://api.sigmora.org/v1/trends?themeId=iab%3A3.1%3A391&windowHours=24" \
  -H "Authorization: Bearer $SIGMORA_API_KEY"

GET /v1/trends returns:

theme-momentum aggregates;
recurring title and hashtag topic clusters within a theme;
explicit controversy-language signals;
recent news-source signals;
the content observations supporting every result;
response freshness (live, recent, aging, or empty);
sampled platform coverage and its limit.

Trends describe what Sigmora’s collectors observed. They do not claim complete coverage of the internet, and a news or controversy signal is not independent verification: follow the evidence links and check facts before you build content on them. Topic clusters report method: lexical-title-hashtag-clustering — they group shared words in titles and hashtags, not deeper meaning.

Get started

Create

Grow & automate

Integrate

Build reliably

Operate

Two different things

The taxonomy

Classify content

Detect a business’s niche

Economics is a prior, not a payout prediction

Viral content

Trend signals

Next steps

Niche discovery

Content autopilot

​Two different things

​The taxonomy

​Classify content

​Detect a business’s niche

​Economics is a prior, not a payout prediction

​Viral content

​Trend signals

​Next steps

Niche discovery

Content autopilot

Two different things

The taxonomy

Classify content

Detect a business’s niche

Economics is a prior, not a payout prediction

Viral content

Trend signals

Next steps