In the
podcast_bias category, which is opt-in — it is callable by name on any connection, but only advertised on tools/list when selected via ?include=podcast_bias. See Tool sets & discovery.LEANS_RIGHT, NOT_POLITICAL). Sort by raw count, or by share of the analyzed catalog to surface publishers whose output is concentrated in the bucket.
Publisher slugs feed particle_podcast_get_publisher. For cross-bucket metrics (most left/right leaning, most diverse), use particle_podcast_get_bias_leaderboard.
Inputs
| Field | Type | Required | Default | Description |
|---|---|---|---|---|
result | string | yes | — | Bias bucket to flip on — which publishers have the most podcasts with this result. One of NOT_POLITICAL, EXTREME_LEFT, LEFT, LEANS_LEFT, CENTER, LEANS_RIGHT, RIGHT, EXTREME_RIGHT. |
political_context | string | no | — | Restrict the corpus to one political framework. One of US, UK, EU, CANADA, AUSTRALIA, INDIA, OTHER, UNKNOWN. |
min_count | integer (1–500) | no | 1 | Only publishers with at least this many podcasts in the bucket. |
sort | string | no | count | count ranks by raw podcasts in the bucket; share ranks by the bucket’s share of the analyzed catalog (surfaces concentrated publishers). |
limit | integer (1–50) | no | 10 | Publishers per page. |
cursor | string | no | — | Opaque pagination cursor. |
Output
A markdown document with## Publishers with <result> podcasts (N) and a flat bullet list — one bullet per publisher, formatted Publisher name (publisher-slug) — N in bucket (X% of analyzed) (the share suffix appears when nonzero). When more pages exist, a horizontal rule and a **Cursor:** <value> line are appended.
Sample (result="LEANS_RIGHT", sort="share", limit=3):
publisher-slug feeds particle_podcast_get_publisher.
Example
Related
- REST equivalent:
GET /v1/podcasts/bias/{result}/publishers. - For cross-bucket metrics, use
particle_podcast_get_bias_leaderboard. - For one publisher’s full bias profile, use
particle_podcast_get_publisherwithinclude: ["bias"].