Player sentiment

• Headlines· Oct 7Media lanes. 1,631 NBA headlines from 23 publishers, Jul 24 to Oct 7. 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. 72% of this week's player mentions have a model rating.
• Fans· Oct 7Fan lanes. 33,561 fan posts: 1,347 headlines from 30 team fan blogs, 2,205 social posts and 30,009 video comments, Jun 25 to Oct 7. 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. 26% 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.

Fan and media tone are kept separate from performance metrics and Movement Center evidence. The privacy page lists what is kept from each source.