Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Twitter's Recommendation Algorithm

blog.twitter.com

Post reply on HN
Print view View original

241–250 of 1001 posts

Re: Twitter's Recommendation Algorithm

#241

Post by minimaxir »

tric wrote: post #11

From 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…

Update: Elon was asked about these in a Twitter Space, he says it's not appropriate and will be removed from the codebase.

Additionally, from another Twitter engineer, the Democrat/Republican flags are apparently 10 years old and not important and do not have high feature importance.

Re: Twitter's Recommendation Algorithm

#242

Post by seydor »

afavour wrote: post #184
jaywalk wrote: post #115

Earlier 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...

Still smells to high heaven to me. Not the Elon part, I don't really care about that. But collecting metrics about "republican" vs "democrat" sounds like a particularly bad set of priorities at work.

but the people who care about stats are usually american politicians. they can present them with this data. (and use Elon as a control LOL)

Re: Twitter's Recommendation Algorithm

#243

Post by EamonnMR »

valarauko wrote: post #101
EamonnMR wrote: post #63

Earlier quoted context omitted.

I sometimes get these as push notifications with my username added to them.

I find these notifications so confusing - at first glance they look like DMs or mentions to me. I don't follow these people, nor were they RT by anybody I know.

Probably lots of engagement due to that confusion though.

Re: Twitter's Recommendation Algorithm

#244

Post by sangnoir »

anigbrowl wrote: post #161
sillysaurusx wrote: post #102

Say what you will about Elon, but this wouldn't have happened without him. Thanks! And thank you to everyone at Twitter who helped organize this release. Open sourcing something like this is no small effort.

I am not sure about that. Twitter has open sourced a lot of stuff in the past. There were certainly people there who would run the site as a nonprofit public service if they had the choice.

Twitter contributed a lot to Map-Reduce, ETL and Scala communities: IMO they punched above thier weight.

Sadly, I think their best open-source contribution days are behind them with all the hardcore engineering they now have to do with fewer engineers.

Edit: I forgot about Bootstrap! That projects saved the world from millions of ugly web apps and dashboards built by clueless backend engineers.

Re: Twitter's Recommendation Algorithm

#245

Post by jdminhbg »

tric wrote: post #124
krapp wrote: post #66

Earlier quoted context omitted.

The repo suggests it's about tracking engagement metrics[0], so Team Red people see more Team Red content and vice versa. Nothing nefarious. [0] https://github.com/twitter/the-algorithm/blob/7f90d0ca342b92...

Why specifically track political parties? Where is author_is_american? Or author_is_mayonnaise_enjoyer? Maybe it was a choice made many years ago that they thought was appropriate, but we can't yet know it's not used for other purposes. We can at least be reasonably sure they've added the author_is_elon within the past year. I would have thought there would be many more descriptors, or non-controversial descriptors.…

The point is probably to check that changes they make aren’t accidentally politically biased.

Re: Twitter's Recommendation Algorithm

#247

Post by ftxbro »

zaroth wrote: post #182
0l wrote: post #151

Earlier quoted context omitted.

> There is code that favor Elon's tweets so I'd yes that's probably what they use Where?

Spoiler - there isn’t.

Yeah they track author_is_elon, author_is_democrat, and author_is_republican but they don't appear to be used for favoritism anywhere in this code.

Re: Twitter's Recommendation Algorithm

#248

Post by bcrosby95 »

lhnz wrote: post #188
NERD_ALERT wrote: post #174

Earlier quoted context omitted.

We don't need to speculate on this. It sounds like he did actually fire engineers over his tweets getting less engagement than he wanted. https://www.platformer.news/p/elon-musk-fires-a-top-twitter-...

Honestly, if you read behind the lines, it sounds like the employee was intentionally making a joke about it at his expense in front of a bunch of people, and I think a lot of CEOs would take that badly as this is effectively the same thing as calling your boss egocentric. But, we do have a bit of code that measures metrics on his account, so can we find the bit of code that increases the engagement on his account?

> “When you’re asked a question, you run it through your head and say ‘what is the least fireable response I can have to this right now?’” one employee explained.

Reading between the lines, Musk sounds like a giant baby.

Re: Twitter's Recommendation Algorithm

#249

Post by thefreeman »

alfor wrote: post #122
simonsarris wrote: post #80

Earlier quoted context omitted.

That would be great (unweighting bluechecks) but they actually plan to go in the other direction: Starting April 15th non-bluechecks won't show up in the "For you" section (the algorithm timeline) at all. Unpaid users are being written completely out of the algo. https://twitter.com/elonmusk/status/1640502698549075972

I don’t see a way out of this with the GPT/AI able to create fake persona in an instant.

What does that matter? If people find the content engaging then it will be amplified. If not, it shouldn't be there in the first place. This whole "AI / Bot swarm" excuse is just smoke and mirrors for "I want more people to pay twitter".

Re: Twitter's Recommendation Algorithm

#250

Post by jytechdevops »

sillysaurusx wrote: post #129
zachnwhite wrote: post #118

Earlier quoted context omitted.

--

I'd be nothing without Twitter. It's had more impact on my life than any other platform. I got lucky, but luck was only part of it. Being able to DM people is incredible. It's the AOL Messenger of 2023. If it went offline, it'd be a terrible loss.

its literally led to the complete change of my future due to the ability to follow the interactions of successful people who are active on the platform. I've learned from them as if they were my direct mentors and made huge life decisions based on some of their talking points / motivational mindset. Without it, my life would've been a bubble in Virginia with my nearest network being 5 friends who love cranking out bottle on the weekends.
Post reply on HN