How fans and media talk about players and teams. The two are shown side by side, never merged into one number.
Data as of Oct 6, 2026Headlines· Oct 61,513 headlinesFans· Oct 630,576 fan postsCurated· Aug 22prototype values, not measured
A language model rates the tone of headlines, fan posts and comments toward the players they name. Team scores and fan posts from before the model still use a word list, so read those as rough.
Sources and method
Headlines· Oct 6Media lanes. 1,513 NBA headlines from 23 publishers, Jul 24 to Oct 6. A player needs 3 headlines in the last 7 days to get a score. A language model rates each headline as positive, neutral or negative toward each player it names. Checked against 127 labeled headlines, it matched the label about 7 times in 10 and never rated one the opposite way. Players named only in the summary, and team scores, still use a word list. 73% of this week's player mentions have a model rating.
Fans· Oct 6Fan lanes. 30,576 fan posts: 1,318 headlines from 30 team fan blogs, 1,882 social posts and 27,376 video comments, Jun 25 to Oct 6. A player or team needs 5 posts in the last 7 days to get a score. Comments under the same video share weight, so 100 comments on one video count for less than 100 posts spread across many places. Fan blog headlines get the same model rating as news headlines. Social posts and video comments that name a player are rated by the same model when they are collected, up to a nightly limit. Checked against 143 labeled fan posts, it matched the label about 3 times in 4 and rated 2 the opposite way. The word list matched about half and rated 18 the opposite way. Older posts, posts past the nightly limit and team scores keep the word list. 17% of this week's player mentions in posts and comments have a model rating.
Curated· Aug 22Hand-written prototype values dated Aug 22, 2026. They show how the board works and are not measurements.
How often the tone rating matches a hand labelSame as the labelOne step offOpposite side
News headlines63 headlines
Language model
71% match0 opposite.
Word list
52% match2 opposite.
Social posts72 posts
Language model
76% match0 opposite.
Word list
44% match6 opposite.
Video comments71 comments
Language model
72% match2 opposite.
Word list
54% match12 opposite.
A coding agent labeled each one positive, neutral or negative toward one named player, not a human panel. One step off means a neutral rating where the label picked a side, or the reverse. The headline set leaves out the half used to tune the word list.
Fan and media tone are kept separate from performance metrics and Movement Center evidence. The privacy page lists what is kept from each source.
League mood · 7d
50% is neutral. The thick line is a 3-day average once there are enough days.
Fan mood
Fans· Oct 6
57% · 27,058 posts
Media mood
Headlines· Oct 6
56% · 1,108 headlines
Fan vs media gaps
Last 7 days · Sep 30 to Oct 6
Where fans and outlets disagree most this week. Open a player to see what each side talks about.
FansMediaTrack runs 0% to 100% positive, 50% in the middle
Ariel Hukporti59%vs11%Fans +48 pts
Fans talk about
brown
knicks
injury
jaylen
scoring
burst
needed
positive
moment
leaves
game
apparent
leg
edgecombe
dominant
looms
preseason
win
56 fan posts, Oct 1 to Oct 6. Words from 3 fan blog headlines.
Media writes about
injury
leg
knicks
non-contact
preseason
right
suffers
center
leaves
opener
scary
undergoing
imaging
achilles
game
brown
ex-knick
five
minutes
debut
heartbreaking
embiid
18 headlines, Oct 4 to Oct 6. Words from 18 headlines.
Bigger words show up in more headlines. Fan words come from fan blog headlines only, because social posts are scored but their text is not kept.
The two lanes are never blended into one score. Both sides here cover the same 7 days, and a gap is only shown when both are measured. A side with only a few mentions can swing a lot, so check the counts when you open a player.
Headline tone
Headlines· Oct 6
Warmest and coolest coverage in the last 7 days, among players with 3+ headlines. Score · headline count.