Our method · step 02 of 10

Detect

The channels’ feeds are read every six hours, their full list every week. The videos of the last seven days go ahead of everything else.

  1. 1Each channel’s feeds are read every six hours.
  2. 2Every week, the full list of each channel’s videos is reread.
  3. 3A detected video enters the queue with its publication date.
  4. 4The videos of the last seven days go ahead of everything else.
Cadence
RSS feeds every 6 h, full listing every week
Priority
the last seven days first, then since April 2026, then the backlog
Writes
detected videos, publication date, task queue
Detection

Three cadences, one queue

Collection, transcription and sentence classification are carried out by the project’s network of computers. The central server hosts the database and this site; it also computes the vectors used for meaning-based search and writes the automatic texts.

  1. every 6 h

    The feeds, every six hours

    The public RSS feeds of each YouTube channel (long videos, Shorts, live streams) give the new videos, their exact publication date and their first view count.

  2. every week

    The full list, every week

    The full list of each channel’s videos is reread every week. It catches the videos missing from the feeds and reveals removals, tracked at step 09. TikTok accounts, which have no RSS feed, are covered by this listing only.

  3. last 7 days first

    The queue and its priorities

    A detected video enters the queue with its publication date. Those of the last seven days always come first, whatever their length; next come the videos published since 1 April 2026, then the batches chosen by the team and the rest of the backlog. A video detected but not yet extracted is transcribed directly.

Last detection: 2 h ago. Of the 48,697 videos tracked, 28,468 have been extracted and 22,822 transcribed; coverage by year is detailed at step 10.

Project paper