Particle Podcast Get Mention Trends
particle_podcast_get_mention_trendsHow a person's, company's or entity's podcast mentions are moving, for tracking it week over week. To find what is rising across all podcasts rather than track a subject you already know, use particle_podcast_get_entity_chart. Two modes:
compare(default): which podcasts mentioned it in a window (default the last 7 days, at most 90) and how each compares with the equal-length window before it: episode and mention line counts in both, the delta, and a label. A show in both windows iscontinuing; one only in the previous isdropped. A show only in the current window is judged against the lookback before it (lookback_days, default 90):newwhen it never mentioned the subject there, published at least four episodes there, and has two or more mention lines now;returningwhen it mentioned the subject earlier in the lookback;passingfor a single line;newly_trackedwhen it published too little in the lookback to tell. Totals for both windows count every podcast. Filter withchange, order withsort(risingandfallingfor the biggest movers), and page withcursor. Answers "which shows talked about Nike this week versus last?" in one call, and, withchange="new"(sorted by popularity unlesssortis set), "which podcasts started talking about Nike this month?" or "which mentioned Nike for the first time?": read what the leading shows said withparticle_podcast_find_mentions. Since 2026-10-23,newno longer means every show absent from the previous window; that set is nownew,returning,passingandnewly_trackedtogether.timeseries: mention counts per day, week or month over a range (omitpublished_afterfor all time), each bucket with its episodes, mention lines and distinct podcasts. Answers "is it rising?".podcast_slugcharts one show.breakdownsplits each bucket by a speaker statement characteristics label (breakdown="sentiment": is it spoken of more negatively this quarter?), andspeaker_statement_characteristicscounts only the mentions said that way ({"temporal_orientation": ["future"]}: are predictions about it rising?); both needpublished_after, at most 365 days back.
Mentions inside ad reads are left out unless include_ads, so a brand that advertises heavily is measured by what shows say about it. The newest day fills in over about a day as episodes are processed, so a window ending now reads slightly low and the current bucket is marked partial: compare full buckets.
Podcast slugs in the response work with particle_podcast_find_mentions (with the same dates as since and until, to read what a show said) and particle_podcast_list_episodes. Not for the mention lines themselves (particle_podcast_find_mentions), appearance or topic trends by role or keyword (particle_podcast_get_episode_timeseries, which counts an episode for a company named only in its ad reads), or a split by who said it (particle_podcast_get_share_of_voice). To be told about new mentions as they air, create an alert with particle_alert_create.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | 'compare' (default): which podcasts mentioned the subject in the window and how each compares with the equal-length window before it, with both windows' totals. 'timeseries': mention counts per day, week or month over a range, with the podcasts carrying them per bucket. | |
| role | No | Constrain how the subject participates: guest, host, panelist, correspondent, or mention. In compare mode the lookback's earlier-mention check counts any mention whatever the role, so a first guest appearance on a show that named the subject before is 'returning', not 'new'. | |
| sort | No | compare only: 'mentions' (most current-window mention lines first), 'rising' or 'falling' (largest gain or loss from the previous window first), or 'popularity' (biggest shows first). Defaults to popularity with change 'new' or 'returning', else mentions. | |
| limit | No | compare only: podcasts per page (1-50, default 10). | |
| change | No | compare only: keep podcasts with this label. 'new': started talking about the subject: two or more mention lines in the window, none in the lookback before it, on a show that published at least four episodes there. Use it for 'which shows started talking about X' or 'mentioned X for the first time'. 'returning': back after a gap in the lookback. 'passing': a single line, a first in the lookback. 'newly_tracked': too little published history to tell (fewer than four episodes in the lookback, which includes a monthly show over the default 90 days: pass lookback_days=180 for those). 'continuing': both windows. 'dropped': the previous window only. | |
| cursor | No | compare only: cursor from a previous response. Pass published_after and published_before as that response's window so the page lines up. | |
| interval | No | Bucket width. timeseries: defaults to week. compare: adds each podcast's counts per bucket over the current window. | |
| language | No | Only podcasts in this language: ISO 639-1 code (e.g. 'fr'), matched on the podcast's primary language subtag. | |
| breakdown | No | timeseries only: also split each bucket's mentions by their label on this speaker statement characteristics axis: breakdown='sentiment' answers 'is it spoken of more negatively this quarter?'. Each bucket's label shares are of its scored mentions, and a bucket with fewer than 20 is marked low sample. Mention counts are unchanged. Needs published_after, at most 365 days before published_before. | |
| entity_slug | No | Knowledge-graph entity slug from particle_entity_resolve for anything that isn't a person or company (e.g. 'germany'). | |
| guest_field | No | Only mentions spoken by a guest listed under this ANZSRC 2020 field of research: a code, slug or title from particle_expertise_resolve. | |
| include_ads | No | Count mentions inside ad reads too. Off by default, so a brand that advertises heavily is measured by what shows say about it, not its own ads. | |
| person_slug | No | Person slug from particle_person_resolve (e.g. 'sam-altman'). One of person_slug, company_slug or entity_slug is required. | |
| company_slug | No | Company slug or domain from particle_company_resolve (e.g. 'nvidia'). Resolves to the company's linked entity. | |
| podcast_slug | No | timeseries only: chart the mentions on one podcast (slug from particle_podcast_resolve). In compare mode the rows are the podcasts. | |
| lookback_days | No | compare only: days before published_after a podcast must not have mentioned the subject in to be 'new' (7-180, default 90; never shorter than the previous window). | |
| output_format | No | Output serialization. 'markdown' (default) returns the LLM-facing rendering. 'json' returns the structured payload as JSON text — use only for programmatic chaining where exact field extraction matters; the JSON shape is larger and noisier for an LLM to read. | |
| guest_capacity | No | Only mentions spoken by a guest who knows their field in this capacity (e.g. 'public_official' for politicians). particle_expertise_resolve names the capacity an everyday word means. | |
| guest_in_field | No | Only mentions spoken by a guest speaking within their own field (the guest the other guest_ filters select, when given). | |
| guest_standing | No | Only mentions spoken by a guest whose standing is recognized this way: 'established' (conferred by others), 'self_described', or 'unverified'. | |
| publisher_slug | No | Only mentions on podcasts of this publisher (network), by slug. | |
| guest_seniority | No | Only mentions spoken by a guest at this seniority or above. | |
| published_after | No | compare: start of the current window (ISO 8601 date or date-time); defaults to 7 days before published_before, and the window may span at most 90 days. timeseries: start of the range; omit to chart all time. | |
| guest_occupation | No | Only mentions spoken by a guest listed under this occupation: a SOC 2018 or ISCO-08 code, slug or title from particle_expertise_resolve, or a SOC group or everyday name (e.g. 'financial-and-investment-analysts' or 'physicians'). A word with no occupation filters by the field of research or capacity it names: 'investors' is field 350208, 'politicians' is capacity public_official. | |
| guest_practicing | No | Only mentions spoken by a guest who still works in guest_occupation, which must be a SOC 2018 occupation or group. | |
| published_before | No | End of the current window or range: a bare date includes that whole UTC day. Defaults to now. | |
| speaker_statement_characteristics | No | timeseries only: count only mentions said a certain way: {"temporal_orientation": ["future"]} charts predictions about the subject; {"sentiment": ["negative"]} criticism. Labels listed for one axis match any of them; axes combine with AND, so add only the axes the request names. Needs published_after, at most 365 days before published_before. |