> ## Documentation Index
> Fetch the complete documentation index at: https://docs.particle.pro/llms.txt
> Use this file to discover all available pages before exploring further.

# particle_podcast_get_mention_trends

> How a person's, company's or entity's podcast mentions are moving: which shows mentioned it this week versus last, or its counts per day, week or month.

Track how a person, company or entity is being talked about on podcasts. It answers "which shows mentioned Nike this week versus last?" and "is it coming up more often?" in one call each, from Particle's own history, so an agent keeps only the slug between sessions and asks again for the window it wants.

The tool has two modes:

* **`compare`** (default): which podcasts mentioned the subject in a window and how each compares with the equal-length window just before it. Each show has its episode and mention line counts in both windows, the change in mention lines, and a label. A show in both windows is `continuing`, and one only in the previous window is `dropped`. A show only in the current window is judged against the lookback before it (`lookback_days`, default 90), and gets the first label that applies:

  * `newly_tracked`: it published fewer than four episodes in the lookback, so there is too little history to tell. A monthly show has only three in the default 90 days; pass `lookback_days=180` to judge one.
  * `returning`: it mentioned the subject earlier in the lookback, then went quiet.
  * `passing`: a single mention line, a name in passing.
  * `new`: two or more mention lines, none in the lookback. It **started talking about** the subject, so `change="new"` answers "which podcasts started talking about Nike this month?" and "which mentioned Nike for the first time?", sorted by popularity unless `sort` is set.

  Totals for both windows count every podcast, whatever page or `change` filter you ask for.
* **`timeseries`**: mention counts per day, week or month over a range, each bucket with its episodes, mention lines and the distinct podcasts carrying them. Omit `published_after` to chart all time.

Mentions inside ad reads are left out unless `include_ads` is set, so a brand that advertises heavily is measured by what shows say about it rather than by its own ads. That is the difference from [`particle_podcast_get_episode_timeseries`](https://docs.particle.pro/mcp/tools/podcasts/podcast-get-episode-timeseries), which counts an episode for a company named only in its ad reads, so a heavy advertiser's count there can be mostly its own ads.

An episode's mentions are counted once it is processed, usually within a day of publication, so a window ending now reads slightly low, and in `timeseries` mode the bucket a window cuts through is marked `(partial)`. Compare full buckets, or end a comparison a day earlier for a settled answer.

## Inputs

| Field | Type | Required | Default | Description |
| - | - | - | - | - |
| `person_slug` | string | one of | — | Person slug from `particle_person_resolve` (e.g. `"sam-altman"`). Exactly one of `person_slug`, `company_slug` or `entity_slug` is required. |
| `company_slug` | string | one of | — | Company slug or domain from `particle_company_resolve` (e.g. `"nike"`). Resolves to the company's linked entity. |
| `entity_slug` | string | one of | — | Knowledge-graph entity slug from `particle_entity_resolve`, for anything that isn't a person or company (e.g. `"germany"`). |
| `mode` | string | no | `compare` | `compare` or `timeseries`. |
| `published_after` | string | no | `compare`: 7 days before `published_before`; `timeseries`: all time | Start of the current window (`compare`) or of the range (`timeseries`), as an ISO 8601 date or date-time. A comparison window may span at most 90 days. |
| `published_before` | string | no | now | End of the window or range. A bare date includes that whole UTC day. |
| `interval` | string | no | `week` in `timeseries` | `day`, `week` or `month`. In `compare` mode, adds each podcast's counts per bucket over the current window. |
| `change` | string | no | — | `compare` only: keep podcasts with one label: `new`, `returning`, `passing`, `newly_tracked`, `continuing` or `dropped`. |
| `sort` | string | no | `popularity` with `change` `new` or `returning`, else `mentions` | `compare` only: `mentions` (most current-window lines first, then the podcasts that dropped the subject, biggest first), `rising` or `falling` (largest gain or loss first), or `popularity` (biggest shows first). |
| `lookback_days` | integer (7–180) | no | 90 | `compare` only: days before `published_after` that a show must not have mentioned the subject in to be `new`, and must have published four episodes in to be judged at all. Never shorter than the previous window. |
| `podcast_slug` | string | no | — | `timeseries` only: chart the mentions on one podcast. |
| `publisher_slug` | string | no | — | Only mentions on podcasts of this publisher (network), by slug. |
| `language` | string | no | — | Only podcasts in this language (ISO 639-1 code, e.g. `"fr"`). |
| `role` | string | no | — | How the subject participates: `guest`, `host`, `panelist`, `correspondent` or `mention`. In `compare` mode the lookback counts an earlier mention in any role, so a first guest appearance on a show that named the subject before is `returning`, not `new`. |
| `include_ads` | boolean | no | `false` | Count mentions inside ad reads too. |
| `guest_occupation`, `guest_field`, `guest_standing`, `guest_seniority`, `guest_capacity`, `guest_practicing`, `guest_in_field` | | no | — | Count only the mention lines a matching guest spoke, as on [`particle_podcast_find_mentions`](https://docs.particle.pro/mcp/tools/podcasts/podcast-find-mentions). |
| `limit` | integer (1–50) | no | 10 | `compare` only: podcasts per page. |
| `cursor` | string | no | — | `compare` only: the cursor from a previous response. Pass the same `published_after` and `published_before` so the pages line up; the response prints them. |

Passing no subject returns `missing_parameter`, and passing two returns `invalid_input`. A comparison window longer than 90 days, `podcast_slug` in `compare` mode, and `change`, `sort`, `limit`, `cursor` or `lookback_days` in `timeseries` mode, and a `lookback_days` outside 7–180, each return `invalid_parameter`. A subject slug that matches nothing returns `unresolved_reference`, so an unknown name is never read as "nobody mentions it".

## Output

**`compare`**: a markdown document headed `## Mention trends — <Name> (<slug>)`, then:

* `**Window:**`: the current and previous windows, to the second, ends excluded.
* `**Episodes:**`, `**Mention lines:**`: the current count, the previous one, and the relative change.
* `**Podcasts:**`: the distinct podcasts in each window and how many carry each label.
* `**Labels:**`: what each label means, with the date the lookback starts.

A `### Podcasts` table follows with each show's title, slug, mention lines now and before, the change, its episodes, and its change label. With `interval`, a line per show lists `bucket-start count` pairs. When more podcasts follow, a paragraph gives the `cursor` with the window to pass alongside it, and a closing paragraph says how to read a show's lines with `particle_podcast_find_mentions`.

Sample (`company_slug="nike", published_after="2026-10-05", published_before="2026-10-11", limit=5`):

```markdown theme={"dark"}
## Mention trends — Nike (nike)

**Window:** 2026-10-05T00:00:00Z to 2026-10-12T00:00:00Z, against 2026-09-28T00:00:00Z to 2026-10-05T00:00:00Z (ends excluded)
**Episodes:** 1,255 (previous 1,309, -4.1%)
**Mention lines:** 3,603 (previous 3,813, -5.5%)
**Podcasts:** 1,099 (previous 1,081, +1.7%): 152 new, 331 returning, 258 passing, 187 newly tracked, 171 continuing, 910 dropped
**Labels:** new = started talking about it: 2+ mention lines now, none since 2026-07-07, on a show that published 4+ episodes since then; returning = mentioned it earlier in that lookback; passing = a single line; newly tracked = too little published history to tell
### Podcasts

| Podcast | Slug | Mentions | Previous | Delta | Episodes | Change |
|------|------|------|------|------|------|------|
| The Annie Frey Show Podcast | the-annie-frey-show | 69 | 0 | +69 | 7 (previous 0) | returning |
| TraderMerlin | tradermerlin | 65 | 3 | +62 | 2 (previous 2) | continuing |
| Shoe Dog Podcast | shoe-dog | 55 | 0 | +55 | 1 (previous 0) | returning |
| The Mileage Podcast | the-mileage | 54 | 1 | +53 | 3 (previous 1) | continuing |
| The 12 Hub Podcast | the-12-hub | 49 | 22 | +27 | 1 (previous 1) | continuing |

More podcasts: pass cursor="…" with published_after="2026-10-05T00:00:00Z" and published_before="2026-10-12T00:00:00Z".

Read a show's lines with particle_podcast_find_mentions, its podcast_slug, since="2026-10-05T00:00:00Z" and until="2026-10-12T00:00:00Z". The newest day fills in as episodes are processed; end the window a day earlier for a settled comparison.
```

**`timeseries`**: a markdown document headed `## Mention trends — <Name> (<slug>) by <interval>`, with `**Range:**` and `**Totals:**` rows and a `### Buckets` table of each bucket's episodes, mention lines and podcasts, the partial ones marked. The range runs from the first bucket's start to `now` when `published_before` is omitted, or to the excluded bound it sets: a bare date includes that whole day, so it shows as the next day.

Sample (`company_slug="nike", mode="timeseries", published_after="2026-09-01", published_before="2026-10-15"`):

```markdown theme={"dark"}
## Mention trends — Nike (nike) by week

**Range:** 2026-08-31 to 2026-10-16 (excluded)
**Totals:** 7,206 episodes, 20,367 mention lines, 4,772 podcasts
### Buckets

| Bucket | Episodes | Mention lines | Podcasts |
|------|------|------|------|
| 2026-08-31 (partial) | 870 | 1,875 | 785 |
| 2026-09-07 | 1,066 | 3,347 | 958 |
| 2026-09-14 | 1,147 | 3,295 | 1,012 |
| 2026-09-21 | 1,197 | 3,632 | 1,037 |
| 2026-09-28 | 1,210 | 3,558 | 985 |
| 2026-10-05 | 1,088 | 3,134 | 955 |
| 2026-10-12 (partial) | 628 | 1,526 | 593 |

A partial bucket covers less than a full week; compare full buckets. For which podcasts drove a change, call again with mode="compare" over that bucket and the one before.
```

A person with no linked knowledge-graph entity gets a note instead of counts.

## Example

```text theme={"dark"}
Agent calls: particle_podcast_get_mention_trends {
  "company_slug": "nike",
  "published_after": "2026-10-05",
  "published_before": "2026-10-11",
  "change": "new"
}
```

It lists the 152 shows that started talking about Nike that week, most popular first: Coffeez for Closers with Joe Shalaby, then SmartLess. The Annie Frey Show's 69 lines don't count, because the show named Nike earlier in the lookback, so it is `returning`. Then read what a new show said:

```text theme={"dark"}
Agent calls: particle_podcast_find_mentions {
  "company_slug": "nike",
  "podcast_slug": "smartless",
  "since": "2026-10-05T00:00:00Z",
  "until": "2026-10-12T00:00:00Z"
}
```

## Related

* REST equivalents: [`GET /v1/podcasts/mentions/by-podcast`](https://docs.particle.pro/podcasts/mentions#which-shows-compared-with-the-period-before) and [`GET /v1/podcasts/mentions/timeseries`](https://docs.particle.pro/recipes/track-a-company#3-chart-the-volume-over-time).
* Read the lines themselves with [`particle_podcast_find_mentions`](https://docs.particle.pro/mcp/tools/podcasts/podcast-find-mentions).
* Split the mentions by who said them with [`particle_podcast_get_share_of_voice`](https://docs.particle.pro/mcp/tools/podcasts/podcast-get-share-of-voice).
* Be told about new mentions as they air with [`particle_alert_create`](https://docs.particle.pro/mcp/tools/alerts/alert-create).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.