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

641–650 of 1001 posts

Re: Twitter's Recommendation Algorithm

#641

Post by suddenclarity »

astrange wrote: post #491
Laaas wrote: post #134

Earlier quoted context omitted.

- Open sourcing this - Lists as tabs - _Heavily_ reduced spam - Can look at Twitter without logging in I'm likely missing some other obvious/uncontroversially good changes. I still use Twitter and plan to continue using it. I am satisfied with most of his changes.

There's not any less spam. How could there be when he laid off all the antispam people? If you expand "see more tweets" sometimes there's normal tweets hiding down there and sometimes it's a bot trying to sell you guns.

How? By having different requirements and implementing another solution? Look at the guy behind YouTube purge tool. One guy accomplished more than YouTube have done for years. Why? No one knows but it's definitely not because lack of resources. I've definitely seen less spam during the last months.

Re: Twitter's Recommendation Algorithm

#642

Post by super256 »

kevincox wrote: post #314
super256 wrote: post #232

Earlier quoted context omitted.

I think it's okay to give Twitter Blue users a boost, as it's most likely not spam (unlike the 95% of my non-blue followers who are bots).

I think it makes sense for out-of-network. However I see no value for boosting among people that I have followed. If I have followed them they definitely aren't spammers (from my PoV).

I agree! Haven't thought of that.

Re: Twitter's Recommendation Algorithm

#644

Post by camjohnson26 »

adharmad wrote: post #621
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…

Also this: https://github.com/twitter/the-algorithm/pull/160

That's a pull request from a random person

Re: Twitter's Recommendation Algorithm

#645

Post by electrondood »

panarky wrote: post #512
roughly wrote: post #153

Earlier quoted context omitted.

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.

The fallacy of false equivalence systematized in code. Now one side can spew as much disinfo and incitement to violence as it likes, and any algorithm change that prevents this shit from getting amplified will be rejected as bias. BSaaS = Both Sides as a Service

Not sure why you got downvoted, you're absolutely correct.

Re: Twitter's Recommendation Algorithm

#646

Post by camjohnson26 »

culi wrote: post #421
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…

what is vits? private val DarkRequestAnnotation = "clnt/has_dark_request" private val Democrats = "democrats" private val Republicans = "republicans" private val Elon = "elon" private val Vits = "vits"

Here's a function definition:

    /**
     * This function returns the top most followed and verified userIds truncated to topK
     */
    def vits(

Re: Twitter's Recommendation Algorithm

#647

Post by hayd »

fanagra32 wrote: post #530
corbulo wrote: post #201

It's disappointing the comments are so obsessed with the political angle to this that there's a total lack of appreciation (or discussion) of opening up the most influential social media platform in the world.

"Opening up"? You must be kidding. Nothing is open there. It's just open-washing. A few nice diagrams, but how the services _actually_ work is still hidden.

> Most of the recommendation algorithm will be made open source today. The rest will follow.

So let's wait and see...

Re: Twitter's Recommendation Algorithm

#648

Post by GuB-42 »

evolve2k wrote: post #639
sillysaurusx wrote: post #450

Earlier quoted context omitted.

Elon seems embarrassed: https://twitter.com/elonmusk/status/1641908130274525187?s=61... It’ll be interesting to see what gets cut. Maybe just the Elon flag, but maybe others too.

Elons reply “I only learned about it now!”. What a crock of shit. We literally went through reporting a few months back where he was clearly instructing the team to make sure his tweets always come up, for everyone.

I think it was more narcissistic than that.

As in: "My tweets are very important, if they don't show up on top, it means the algorithm can't recognize what is important, it needs to be fixed". And the team, who probably didn't see in which way Elon Musk's tweets could be that important besides the fact that he wrote them, they just decided to give Elon Musk's tweets a boost.

Re: Twitter's Recommendation Algorithm

#649

Post by suddenclarity »

ryzvonusef wrote: post #401
suddenclarity wrote: post #391

Earlier quoted context omitted.

Might be a language barrier from my side but it doesn't really sound like a "strange quirk" but rather a wise decision. Following people to get followers is one of the oldest spam methods on social media. It's not surprising that they would reduce the reach of accounts using those methods.

good point! "interesting insight" might have been a better phrase. i am just skimming twitter to get some scoops on the algo release

And I appreciate it. I'm looking forward to people analysing all of it so we eventually can get an in-depth lecture on both the techniques and their decisions.

Re: Twitter's Recommendation Algorithm

#650

Post by mirkules »

yurodivuie wrote: post #613
correlator wrote: post #407

Earlier quoted context omitted.

There is clearly a lot of information to share. It's worth considering this could be step 1 of n as opposed to assuming the worst possible intention.

It's healthy to have a normal amount of cynicism. They released it for a reason. "The goal of our open source endeavor is to provide full transparency to you, our users, about how our systems work." Why be transparent (or try to appear transparent)? To convince people to trust your platform (or to recruit - which seems to be another goal of the post). Why would Twitter want or need to do this now? Well, there is a bi…

I love this take. Doomed if you do, doomed if you don't.
Post reply on HN