221–230 of 1001 posts
Squashing the commit history before releasing it was an interesting (and completely predictable) decision.
[1]: https://github.com/twitter/the-algorithm/blob/7f90d0ca342b92...
> Twitter has several Candidate Sources that we use to retrieve recent and relevant Tweets for a user. For each request, we attempt to extract the best 1500 Tweets from a pool of hundreds of millions through these sources. We find candidates from people you follow (In-Network) and from people you don’t follow (Out-of-Network). > Today, the For You timeline consists of 50% In-Network Tweets and 50% Out-of-Network Twee…
Earlier quoted context omitted.
I believe LeBron James said recently he isn't going to waste his money on a blue checkmark, so it should be interesting to see what stays and what goes.
LeBron doesn’t get $84 of value from Twitter? Definitely not a political statement going on there.
(Note that I use discriminate in the literal sense, as a simple statement of fact.)
For ranking the candidates these predictions are combined into a score by
weighting them:
"recap.engagement.is_favorited": 0.5
"recap.engagement.is_good_clicked_convo_desc_favorited_or_replied": 11* (the
maximum prediction from these two "good click" features is used and weighted by
11, the other prediction is ignored).
"recap.engagement.is_good_clicked_convo_desc_v2": 11*
"recap.engagement.is_negative_feedback_v2": -74
"recap.engagement.is_profile_clicked_and_profile_engaged": 12
"recap.engagement.is_replied": 27
"recap.engagement.is_replied_reply_engaged_by_author": 75
"recap.engagement.is_report_tweet_clicked": -369
"recap.engagement.is_retweeted": 1 "recap.engagement.is_video_playback_50": 0.005
Earlier quoted context omitted.
AGPL is probably useless for any other site who'll want to use it, as it would require them to open source their site that uses it.
Mastodon is conveniently also AGPL...
Earlier quoted context omitted.
LOL. My algorithm at twitter had been very simple- See tweets from people I followed. Don't see tweets from people I didn't follow. Trust people I follow in their retweets to signal something interesting. Unfollow unhelpful people. Once that algorithm was rendered impossible, I left twitter. Haven't missed it. Having someone say- here's the way we are going to promote something to you- doesn't make me inclined to acc…
This still exists as the Following tab and viewing it is a persistent option. You don’t need to see the algorithm feed (“For You”) ever.
20-25% noise isn’t a great ratio for something that I ostensibly curate.
> Twitter has several Candidate Sources that we use to retrieve recent and relevant Tweets for a user. For each request, we attempt to extract the best 1500 Tweets from a pool of hundreds of millions through these sources. We find candidates from people you follow (In-Network) and from people you don’t follow (Out-of-Network). > Today, the For You timeline consists of 50% In-Network Tweets and 50% Out-of-Network Twee…
So as expected, there is exactly nothing that favors posters from one side of the political spectrum. I don't expect that this article will do anything to calm down those who are convinced otherwise though. Well written article, from an engineer's perspective.
Ranking is achieved with a ~48M parameter neural network that is continuously trained on Tweet interactions to optimize for positive engagement (e.g. Likes, Retweets, and Replies). This ranking mechanism takes into account thousands of features and outputs ten labels to give each Tweet a score, where each label represents the probability of an engagement. We rank the Tweets from these scores.