What every number, badge and emoji on the site means, and how it's made. Everything here is
computed on one home computer, every hour, from the front pages of the outlets we follow.
📡 Where the news comes from
🗞️Outlets and front pages
We follow 237 outlets and read what's on their front pages every hour. 111 are read
straight from their homepage, 89 from their own RSS feeds, 0 through Google News
(outlets that block readers like ours), and 37 with a real browser (pages built by
JavaScript).
A headline is live while it's still on a front page. When it drops off, we keep it,
which is how the site can say an outlet dropped a story (👻) or rewrote a headline.
🧹News, not everything
Front pages carry shopping guides, horoscopes and recipes too. A language model labels every new headline
as news, not news, or page junk; only news counts toward stories, the cloud and the measures below.
Very short or very long "headlines" and text repeated across a page are dropped as navigation.
🤖 How headlines are read
🤖The language model
A small open model, qwen3:8b, runs on our own computer (not a cloud service). It reads
each new headline once and answers in a fixed format: whether it's news, whether it presents the news as good or bad,
how loaded the wording is, and the feelings it's most likely to stir. Before scoring, it writes a short
note on how the headline treats the news and for whom, which keeps its answers grounded. It makes mistakes, so treat any one score as
a rough read; the averages over many headlines are what the site shows.
🌦️Mood
Whether a headline presents its news as good or bad, from grim to upbeat (⛈️ 🌧️ 🍞 🌤️ ☀️; "+" means
more so), judged from the outlet's own words and tone. The same court ruling can be 🌧️ grim in one
outlet's headline, ☀️ upbeat in another's and 🍞 plain in a wire report's: that difference is the
outlets' framing. Plainly reported deaths and disasters are grim. A story's mood is the average of
its headlines. (Until Oct 4, mood was how good the event was for the people it affects, whoever
reported it; for anything political that meant the model taking a side.)
🌶️Spin
How much a headline's own wording adds emotion, judgment or alarm beyond the facts: 🍞 plain, 🌶️ loaded
(a charged word or two, like "slams" or "chaos"), 🌶️🌶️ loaded+ (built to provoke). Words quoted from
someone don't count. Outrage bait counts even in plain words ("Oh, come on:", "You can't make this
up").
😱Feelings
The feelings a headline is most likely to stir in a reader, ranked, up to three, from:
😱 fear, 🤬 anger, 😭 sadness, 🤮 disgust, 🤯 surprise, 😄 joy, 🤞 hope, 🥛 neutral.
Like ranked-choice voting, each headline's vote is split 3:2:1 across its picks, and a story's or
word's feelings are the average of those votes. A story card shows every feeling with
20% or more of the votes; 🥛 neutral is plain information.
📚 Stories and sagas
📰Stories
Headlines about the same event, from different outlets. Each headline is turned into a meaning
fingerprint by a sentence-embedding model running on our own machine (mxbai-embed-large), and headlines
whose fingerprints are close enough (0.8+) join up; a story needs at least six
outlets. Stories look back 24 hours, so an outlet that
dropped one still shows on its card, faded with a 👻. The language model writes each story's title.
Covered by on a card (🫏 to 🐘) is the average lean of the outlets covering it, compared
with all the outlets we follow, which lean left as a group. Arrows beside a meter show it moving over
the last few hours: ◀ or ▶ as coverage shifts toward left- or right-leaning outlets, ▲ or ▼ as the news
turns brighter or grimmer; more arrows, more movement.
🧵Sagas
One running story told across several stories: the Cornell case's allegations, the prosecutor, the attorney
general taking over. Two stories join a saga when their centers are close (similarity 0.54+)
and they share a distinctive name, one in at least 30% of both stories'
headlines but no more than 4% of the day's, that outlets capitalize as a name
(Cornell, Iranian), not a common word (rally).
Sagas are kept: each hour today's stories are compared with the last week's, so a saga gathers stories
across days and never loses one when its earlier stories leave the front pages. A saga shows while any
of its stories is current; those that have left the front pages are listed, quieter, with when they ran. A saga counts once in
the top stories, by its story on the most front pages now.
🌈Arcs
The big affairs, followed over weeks: the US–Iran war, the midterms, the Russia–Ukraine war. An arc is
the whole affair; its threads are the turns of it. So a war and the talks that might end it can be
followed apart and together. Arcs are opened and described by Claude (Anthropic's AI model); a local
AI model then places each running story in an arc, or in none. Most sagas belong to no arc, and that's
fine: an arc is only for an affair big enough to be told as several threads at once.
Every arc is with the sagas at the foot of Every story.
🧵Threads
One turn of an arc, followed as it develops: one front, one negotiation, one race, one court case, one
decision and its fallout. The midterms are an arc; the Alaska Senate race is a thread of it. The
Iran war is an arc; the Hormuz blockade and the talks in Qatar are two of its threads.
A thread is a saga that sits inside an arc, and it's made differently. Once a week a local AI model
reads every story in the arc at once, names its threads (a name and a sentence on what belongs) and
puts each story in one. In between, new stories join a thread hourly, and two threads are never
merged. The model sometimes names a thread too broadly (a whole election's gains, not each race),
so a thread can hold more than one turn.
From small to big: a story is one event, a saga is one running story, a thread is
a saga inside an arc, and an arc is the whole affair.
📰Front pages now, over its life
A story is “on 21 front pages now” when 21 outlets have a headline on it on their front page at our
latest look, and has “70 front pages over its life” when 70 outlets have had one there at any time
since it began; a saga's life takes in all its stories. Its peak is the most front pages that had it at
one hourly look. The top stories, and the top story the news-day sticker names, are the stories on
the most front pages now, however old. Aggregators (Google News, Drudge…) link to other outlets'
stories and never count.
🚨News day
How big a news day it is: the share of outlets carrying one story on their front page right now,
each weighed by how fresh its own latest headline on it is (full weight for 2 hours,
then halving every 3), so everyone writing about one story at once counts in full and
yesterday's headline left up fades. The day is as big as its biggest hour in the last
12. 45%+ is a big news day, 25%+ just another news day, less
a slow one.
🚀Speed of break
How many outlets had a story within 75 minutes of our first sighting (two hourly
reads). 8+ earns the rocket.
🙈Blindspots
Stories almost only one side is covering: at least 6 rated outlets, 70%+
of them from one side, and that side's share at least 1.5× its share of all our rated
outlets. Their story cards carry a 🙈 label and a meter of who's covering them (blue left, gray center,
red right) with a tick where an average story would split; the 🙈 button above the cards shows only
blindspots.
☁️ The word cloud
☁️Size and color
The 95 words and phrases the most outlets are using right now; each outlet counts once
per word, so a busy outlet can't inflate one. Bigger means more outlets.
Color is who uses a word more readily: blue for left-leaning outlets, red for right, a blue-to-red blend
for both, gray when it's mostly center outlets. Each outlet's use is weighted by how many distinct words
it publishes, so high-volume outlets don't tilt everything their way.
😰Emoji bookends
A word framed by emoji (😰death😱) has a strong feeling in its headlines: at least 25% of
the votes, among words 5+ outlets use; the 25 strongest get them.
📏Sorting
Words are packed at tilts (bigger ones closer to level) and drift along the arrow behind them: biggest
first by default, or left to right, or plain to spicy. Click a word to see how outlets are using it.
📏 Other measures
📢Buzz
In the headline table: how much a headline uses the words and phrases everyone else is using today,
as a percentile of the day's headlines (📢 top 5%, 🔊 top 20%, 🔉 top half, 🔈 low, 🤫 quiet).
😈Framing
On the outlets page: on stories other outlets also covered, whether an outlet's headlines make the same
event look worse (😈 gloomier) or better (😇 sunnier) than everyone else's. Comparing within a story
separates how an outlet frames the news from which news happens to be bad.
✏️Headline changes
Headlines an outlet changed on an article it had already published, over 7 days. A change
counts only if the old headline left before the new one appeared; live blogs, reused links and minor
changes (capitalization, punctuation, a label like "WATCH:") are skipped.
📡Wire copy
On the outlets page: the share of an outlet's headlines over the last week that are AP or Reuters
headlines, word for word or nearly (very close in meaning and sharing most of their words). Outlets
mostly rewrite wire stories in their own words; this counts only the ones they run as is.
📌Aggregators
Google News, Drudge Report, RealClearPolitics and Political Wire mostly link to other outlets' stories,
so they don't count as outlets covering a story, or toward lean, the news-day sticker or the cloud. A
story card says "📌 picked up by" when one of them is linking to it right now.
🔎Investigations
The newest pieces from open-source and investigative outfits (Bellingcat, ICIJ, OCCRP, DFRLab, Citizen Lab,
Just Security), read from their feeds once an hour. They publish a few deep pieces a week rather than a
front page, so they're listed on their own and don't count toward stories, the cloud or any measure.
📰 in the news marks one that matches a current story.
🎙️On the shows
The newest from news-of-the-day podcasts, newsletters and political streams (Pod Save America, Breaking
Points, Up First, Ruthless, Megyn Kelly, Hasan Piker…), one per show, read from their own feeds every
couple of hours. We sort shows by how they follow the news, not by format: news of the day
shows react to this week's news, several stories at a time; thinking shows take one subject
at a time (The Remnant, Noahpinion). Only news-of-the-day shows appear here; we keep a record of the
rest for research. Blue, red and gray mark a show's rough side by reputation, not a rating.
📡Trending elsewhere
What's trending on Bluesky, Google searches, Wikipedia's most-read pages and Mastodon, next to what the
press is covering. A trend tagged news matches one of our stories.
🧶 Folklore and motifs
The other half of the site: the stories people tell about the news, on the shows we
transcribe, online and to fact-checkers, sorted into shapes the way a folklorist sorts tales. A story people
tell is not a claim that it's true.
The shape of a story as its tellers tell it, named the way a folklorist names a tale type: without
names or dates, so the same story told about other people, by the other side or in another year lands
in the same place. A language model files each claim it reads under the motifs it fits, and Claude
(Anthropic's AI model) checks them, with the person who runs the site spot-checking; only motifs and
claims that have been checked are on the site. All of them are in
the motif index, each with a page of its claims.
The layer of story a motif is, given when it's checked: a kind of person, what happened, a premise, what
people think is behind it, a move in an argument, and so on. A genre belongs to a motif, not to a
claim. Wherever motifs are listed by color, the five biggest genres (most of what's told) have their
own colors, always with their emoji; the smaller ones stay white, known by their emoji:
A motif rests on another when it only makes sense given that one: a kind of it, or a case, an argument
or a figure that tells it. Voter fraud rests on Rigged election. It's the index's one hierarchy, and it
can cross genres. A motif's page lists what it rests on and, as ⤵️ under it, what rests on it.
Arguing against a story is often a story of its own: its answer. Voter fraud is answered by Voter
suppression, Lawfare by No one is above the law. We link the two, and the argument against is
filed under the answer; where no answer has a motif yet, it sits with the story's own tellings. A
motif's page lists them under ↔️ answers and mirrors; on the aisle, an arc joins each pair.
📋copiedown words🗣️
🗣️Copied or in their own words
On a story retold online: how much the posts telling it share the same
words. Folklore travels as variants, each teller putting it their own way, so its dot sits toward 🗣️
own words; copypasta and coordinated posting are the same words pasted, toward 📋 copied. The dot is
how much one version's words turn up in another, on average.
📏0no more apart than chance
📏The divide
How different the stories left and right shows tell are, week by week (Tuesday to Monday), on the aisle: the mix of motifs said by the hosts and guests of
left-leaning shows against the mix on right-leaning shows, less how different the same shows look when
split into two sides at random (500 times). 0 means no more different than
shows picked at random; higher, further apart. Weeks only: a day has too few tellings. Weeks before
Oct 20 rest on partial transcripts.
🗺️The aisle
The motif map: every motif the shows told is a dot, placed left to right by
the share of the shows whose host or guest said it that lean left or right (a clip a show played, or a
caller, doesn't count; a motif few shows said sits nearer the middle), and higher the more it was told.
A ringed dot is rising: told at least 3 times this week, and twice as often as
the week before. An arc joins a
story to its answer. Below the map, ranked lists in pairs: rising and fading, mostly left and mostly
right, told on both sides and only in the center.
🎙️ Theo Von🎙️ The Tim Dillon Show
🔀Crossover shows
Shows we don't put on the left or the right, whose hosts and audiences cross the usual lines:
The Focus Group, Surrounded (Jubilee), Racket News, Theo Von, The Jimmy Dore Show, The Tim Dillon Show, Danny Jones Podcast, Flagrant, Call Her Daddy, The Breakfast Club, Lex Fridman Podcast, Real Time with Bill Maher, Club Random with Bill Maher. Show leans are our own rough grouping by reputation, not a rating, in
purple wherever shows are colored by lean. The aisle leaves crossover shows out of its two sides and
lists, when there are any, the motifs said on 2 or more crossover shows and on no
other; the Replay gives them a lane of their own.
🔁3+shows, word for word
🔁The Replay
The passages heard word for word on many shows this week: a clip of a
speech or an interview, a campaign ad, a statement read out, a sponsor read. We find them in our own
machine transcripts of the shows' episodes: the same 12 words in the same order on
3 or more different shows. Each clip shows when and where it aired, in a lane
for each lean of show.
⚖️ Outlet ratings
⚖️Lean: AllSides
Each outlet's lean is AllSides' Media Bias
Rating (CC BY-NC 4.0), on their five
levels: Left, Lean Left, Center, Lean Right, Right. Outlets AllSides doesn't rate are shown dashed and
"not rated", and are left out of every lean average.
✏️Our estimate (est.)
For outlets AllSides doesn't rate, we estimate lean from the wording of their headlines over
30 days, with a model trained on the rated outlets. It publishes only when the model
checks out (tested by hiding each rated outlet in turn, its rank agreement must be
0.45+) and it's confident about the outlet.
Right now it calls a side for 36 of the
119 rated outlets in that test, and gets
97% of those right; 8 outlets carry an
estimate. Estimates are dashed "est." chips, and they stay out of lean averages.
📚Reliability: Wikipedia
Whether Wikipedia's editors treat an outlet as a reliable source (generally reliable, no consensus,
generally unreliable, deprecated), from their perennial sources
list (CC BY-SA 4.0). It's a judgment about
citing a source, not a fact-check score.
🔨 How it was built
📓 Every change to how we collect and measure things, dated, with what didn't work and the
mistakes we caught: the methods log.
✍️2024: by hand
The site began in January 2024 as Maudlin, designed and written mostly by hand: the scrapers for each
outlet, the database, the word cloud and the first sentiment measures, over about 680 commits through
August 2024.
🛠️2026: rebuilt with AI assistance
For the 2026 midterms it was rebuilt with an AI coding assistant (Anthropic's Claude), starting in
October 2026. The ideas, the design, the research questions and every decision about what ships are a
person's; the assistant wrote and tested much of the new code to that direction, and helped research
sources, ratings and methods.
🧠Two different AIs
Building the site is one thing; reading the news is another. The measures on this site (news or not,
mood, spin, feelings, story titles) come from the small open model described above,
qwen3:8b, running on our own computer. Every score records which model and which version
of its instructions made it, and we test how stable its answers are before trusting them, including
publishing where it fails.
🚧 Limits
🗞️Front pages, from a left-leaning mix
Front pages, not readership. We measure what outlets put up front, not what people read
or share.
Our outlet mix leans left as a group; lean measures compare against that mix, and
blindspots account for it.
🤖The model makes mistakes
Single scores are rough; averages over many headlines are steadier. Small models also shift with how a
question is worded, which is why we test stability before trusting a measure.
📅Young data, mostly US
Young data. Our database starts on October 2, 2026, so stories that were already running
then look newer than they are, and 30-day measures are still filling in.
Mostly US. Stories, sagas and lean use US outlets plus a few British ones; we follow
foreign outlets for the cloud and the outlets page.
Reusing it. How we work is open: the methods log is
CC BY 4.0, credit bignews.day. The motif
index, our readings and our other writing are all rights reserved: ask us before reusing them, and ask
about research use. The lean ratings and the reliability list keep their own licenses, below each page.