Is it even what they use in production? There is code that favor Elon's tweets so I'd yes that's probably what they use
> There is code that favor Elon's tweets so I'd yes that's probably what they use
Where?
Twitter's Recommendation Algorithm
151–160 of 1001 posts
Re: Twitter's Recommendation Algorithm
#152My main questions: Will these repositories be used in production by Twitter? Is this now the mainline, not a semi-regularly-synced mirror?
Re: Twitter's Recommendation Algorithm
#153From https://github.com/twitter/the-algorithm/blob/7f90d0ca342b92... ( "author_is_elon", candidate => candidate .getOrElse(AuthorIdFeature, None).contains(candidate.getOrElse(DDGStatsElonFeature, 0L))), ( "author_is_power_user", candidate => candidate .getOrElse(AuthorIdFeature, None) .exists(candidate.getOrElse(DDGStatsVitsFeature, Set.empty[Long]).contains)), ( "author_is_democrat", candidate => candidate .getOrEls…
Only used for metrics, apparently. [0] /** * These author ID lists are used purely for metrics collection. We track how often we are * serving Tweets from these authors and how often their tweets are being impressed by users. * This helps us validate in our A/B experimentation platform that we do not ship changes * that negatively impacts one group over others. */ [0]: https://github.com/twitter/the-algorithm/blob/7f…
I expect they're tracking the red team/blue team metrics because of the political shitstorm that's been the GOP's assertions they're being silenced by The Algorithm.
Re: Twitter's Recommendation Algorithm
#154Earlier quoted context omitted.
Twitter has this now. The home page is split into two tabs: "For you", the algorithmic feed, and "Following", the reverse chronological feed of just who you follow.
Is really "Following" the entire chronological feed? I feel I miss tweets from people I follow that actually appears in the "For You" tab.
It's not. I follow a fairly small # of people (~500) and getting people to reliably show up in is a long-running problem. Following is not enough, you have to favorite or somehow interact with them sufficiently to be sure of seeing all their tweets. It's quite annoying.
Re: Twitter's Recommendation Algorithm
#155Re: Twitter's Recommendation Algorithm
#156Earlier quoted context omitted.
\* \* These author ID lists are used purely for metrics collection. We track how often we are \* serving Tweets from these authors and how often their tweets are being impressed by users. \* This helps us validate in our A/B experimentation platform that we do not ship changes \* that negatively impacts one group over others. \* From: https://github.com/twitter/the-algorithm/blob/7f90d0ca342b92...
That makes sense; I guess that means Elon is considered a "group" now.
I know there's a joke about this regarding his ego and there's certainly some truth in that, however it's also quite believable that after a deployment he might have noticed the popularity of his tweets going down (since he no doubt checks his reach), so I can kind of understand how he might see "republicans", "democrats" and "celebrities_it_makes_sense_to_check_this_with_my_account_as_i_am_a_very_active_user" as core categories that need to have their reach balanced.
Re: Twitter's Recommendation Algorithm
#157Is it even what they use in production? There is code that favor Elon's tweets so I'd yes that's probably what they use
Humorous conspiracy theory: Imagine if it is not, but sanitized, and then someone added in Elon Boost to make it look credible. :-)
Re: Twitter's Recommendation Algorithm
#158Context: I teach at Princeton and study social media and recommendation systems. From a very quick skim of the repositories, this appears to be quite limited transparency. The documentation gives a decent high-level overview of how Tweet recommendation works—no surprises—and the code tracks that roadmap. Those are meaningful positive steps. But the underlying policies and models are almost entirely missing (there are…
What did you expect?
Re: Twitter's Recommendation Algorithm
#159This is pretty limited. I picked a term used in the diagram to see what I could find out about it. But there seems to be next to nothing in the released code about the mentioned "author diversity". No real code or description.
I think the relevant part of the code is in this other repo:
https://github.com/twitter/the-algorithm
Not sure if it has what you were looking for (and maybe you already checked this repo, too!), but it's more relevant than the linked repo imo
Re: Twitter's Recommendation Algorithm
#160Let's dig into Twitter code quality.
https://github.com/twitter/the-algorithm/blob/7f90d0ca342b92... ``` def query_keys(self, language, task=2, size="50"): if task == 2: if language == "ar": self.query_settings["adhoc_v2"]["table"] = "..." elif language == "tr": self.query_settings["adhoc_v2"]["table"] = "..." elif language == "es": self.query_settings["adhoc_v2"]["table"] = f"..." else: self.query_settings["adhoc_v2"]["table"] = "..." return self.query…
Looking through it, the ... seems to be a placeholder for information they'd prefer to be kept private. For example, look in the keywords section in the same file you shared.