How this page is built.

YouTube does not publish daily view counts for other people's videos, so nobody outside YouTube can list the day's most-watched with certainty. What can be measured is the US trending chart, and momentum inside it. Each morning we gather around 450 candidates from YouTube's public charts for the United States, the plain most-popular list first and then ten categories from news and sports to music and gaming, plus a search for the most-viewed uploads of the last two days. A video on the plain US chart that clears the comment floors is taken before a category-chart video, and a category-chart video before a search-only one. Search with a US region only means the video can be watched here. Inside each of those three groups we rank by the geometric mean of views per hour and comments per hour since upload, with a small penalty after a day and a half, and take the first five that pass a fixed filter. A view-count spike whose comment section never showed up sorts behind a video people are actually writing on.

A video is skipped if it is a live broadcast or a Short (including a hashtag like #sportsshorts), or a clip of three minutes or less with fewer than 800 comments; if it went up less than eight hours ago, or more than three days ago (two weeks, for a video still on the plain US chart); if comments are off, fewer than 400, or thinner than one per 20,000 views; if YouTube reports it private, deleted, or region-blocked, or it is on a short list of ids already known to be gone; if it has already had its day here; or if its channel is already in the edition. A channel that ran in the last three days waits, and a channel that already has two videos in the last fourteen days waits too. A numbered series, a title carrying Day, Episode, or Part and a number, waits fourteen days, so tomorrow's episode of the same show does not take the slot. That series wait applies only once an earlier episode has already run here, so the first one we see still competes. Near-duplicate titles are dropped, and at most two videos come from any one category. Music is that cap of two, and only one of those may be a music video from a K-pop label. The next chart video fills the slot. The channel waits, the fourteen-day channel cap, the near-duplicate check, the category cap, and that K-pop cap give way only when keeping them would leave the edition short. The series wait does not. Two backups are saved with the five, and one is promoted if a pick's comments turn out unreadable, instead of publishing a hole.

Language is not part of that filter. A video in any language keeps its place when the numbers say it earned one. When YouTube's language tag, the title, or the comments we read are not English, the card and the video page offer a Translate link to this page, label the description as an English summary, and point at YouTube, where captions can be auto-translated. The summary is the same model call as every other card, asked to write in English.

Nothing is chosen editorially and nothing is chosen for how it will read. When fewer than five survive, the edition runs short and says so.

For each video we fetch up to a thousand top-level comments. Sentiment, recurring themes, emoji counts, comment timing, and the automation estimate are all computed in ordinary code on our own servers, not by a language model. That is a deliberate choice: it is free, it is fast, and it gives the same answer twice for the same input.

A model is used for exactly two things per video, because neither is possible in code. It watches the first twelve minutes of the video to say what the video is, in English, including when the video itself is not. And it picks the funniest comment from a shortlist of about 25 that code has already narrowed down by likes, length, and cleanliness. Everything else it is shown is a summary of numbers we computed first. When that call fails, the shortlist's own ranking is what gets published, and this page is where that is recorded.

Sentiment is scored with a weighted word list written for comment sections specifically, including slang a general-purpose list gets backwards: “sick”, “insane” and “goat” are praise here, “mid” and “cooked” are not. Negation flips a score, intensifiers scale it, shouting amplifies it, and emoji count.

It cannot detect sarcasm. It only reads English, so on a card that is not in English the mood figure is a weaker signal and the Translate link is how to read the section. On a single comment it is noisy and sometimes simply wrong. Across a thousand comments the direction is meaningful, which is the only level the page reports it at.

The automation figure is an estimate of how much of a comment section did not look like a person typing. It weighs observable signals: identical text posted by several different accounts, known scam and engagement-farm phrasing, links and phone numbers, hidden characters used to dodge filters, very new accounts, accounts with no uploads, and comments posted within minutes of upload. No single signal is enough on its own, because plenty of real people have new accounts and auto-assigned handles.

We never label a named account a bot. Calling a specific person automated is a factual claim about a human being, made by a heuristic with no way to verify it. So per-comment scores are never stored, never published, and never attached to a name. Only the aggregate is reported, and any comment that scores as possibly automated is excluded from being quoted at all.

Comments are analysed in memory and thrown away. What we keep is our own analysis, which contains no comment text and no author names, plus at most six featured comments per video, held so the page can quote them.

YouTube's API terms require stored data to be refreshed or deleted within 30 days. Every day the pipeline re-checks any stored comment or statistic older than 25 days against YouTube. If a comment has been deleted there, its text is deleted here and the page says so in its place. Our own commentary about it stays, because that part is ours.

Video titles, thumbnails, statistics and comment text come from the YouTube Data API and belong to their creators and authors. Every comment and video on this site links back to its original. Sentiment, themes and automation figures are PAID LLC's own estimates and are not YouTube metrics.

PAID LLC is not affiliated with or endorsed by YouTube or Google.

If your comment is quoted and you would rather it were not, or if something on this page is inaccurate, write to us and it will be removed or corrected. Deleting the comment on YouTube also removes it here within a day.