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

551–560 of 1001 posts

Re: Twitter's Recommendation Algorithm

#551

Post by db48x »

threeseed wrote: post #478
mochomocha wrote: post #192

Earlier quoted context omitted.

... Metrics tracked in AB test. So even if it's not explicitly encoded in the algo (or implicitly through some of the features plugged in), they'll pick the winning cell as long as it doesn't hurt Elon's metrics (I'm just parroting the comment you quoted). It doesn't have to be in the algorithm for the systems to be tweaked to please Elon vanity metrics. [I've been running lots of ML AB tests over the years, some in…

That lines up with reporting from Casey Newton a few days ago where a handful of VIPs e.g. Musk, LeBron James, AOC were being used as weather vanes to understand what the algorithm was doing. It definitely isn't just metrics. Any algorithm change that negatively affected Musk was clearly not going live.

Do you think the code looked like that prior to Elon's purchase? I suspect that there was another name there before.

Separately, which of these groups do you think that they use as a control?

Re: Twitter's Recommendation Algorithm

#553

Post by andy_ppp »

CathalMullan wrote: post #55
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…

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…

But who chooses the users to be metrics…

Re: Twitter's Recommendation Algorithm

#554

Post by krapp »

ClumsyPilot wrote: post #466
krapp wrote: post #109

Earlier quoted context omitted.

I don't believe echo chambers are nefarious - there's no hidden agenda involved with them. That's just how recommendation algorithms work, and it's what most people want. But if someone finds some code that suppresses recommendations from a specific political ideology across the board, that would be nefarious, IMO.

[flagged]

I don't believe repeating someone's comment nearly verbatim is as clever as you want it to be, nor do I believe recommendation algorithms are equivalent to the kinds of societal discrimination you allude to, nor would any reasonable person.

Instead of trying very hard to be clever, please next time try just as hard to make a valid point. I know it can be difficult when you think you smell karma in the water but do try.

Re: Twitter's Recommendation Algorithm

#555

Post by dmix »

schemescape wrote: post #441
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…

Did they not expect people to notice suspicious code like this? Or did they leave this in just so they could hold its removal up as an example of listening to the community?

Why are you assuming this knowledge is harmful to them? What do you think it means for their business?

No other social media platform will have this sort of accountability and public pressure to be better like having their recommendation algorithms public.

Re: Twitter's Recommendation Algorithm

#556

Post by XorNot »

sschueller wrote: post #237
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…

Well someone just asked about it in the live spaces[1] Elon is hosting and he said that should not be there. An engineer said afterwards it is just for metrics but then Elon chimed in again and said "we should get rid of it, it should be gone." [1] https://twitter.com/elonmusk/status/1641880448061120513?s=20

Of course he did because it makes him look bad and he's desperate for praise and attention.

What he wanted was everything that feature provides, without it ever being shown that it's there. But since he refuses to hire PR people and almost certainly came up with this idea in the last few days, no one was paid to hide its existence.

The next story out of Twitter will be the remaining engineers being threatened because Musk can't see his tweet statistics any more.

Re: Twitter's Recommendation Algorithm

#557

Post by rogerallen »

bluetidepro wrote: post #87
rogerallen wrote: post #38

"Today, the For You timeline consists of 50% In-Network Tweets and 50% Out-of-Network Tweets on average, though this may vary from user to user." I have spent significant effort creating a network and there you go choosing to ignore my efforts by putting in 50% of crap-I-don't-want-to-see. That is why I despise your algorithm.

> "Today, the For You timeline consists of 50% In-Network Tweets and 50% Out-of-Network Tweets on average, though this may vary from user to user." I have spent significant effort creating a network and there you go choosing to ignore my efforts by putting in 50% of crap-I-don't-want-to-see. That is why I despise your algorithm. This is just one feed (the "For You" recommendations feed), they also have the "following…

I said I despised the algorithm, I did not say I hated Twitter. Now I at least know why I hate it.

Yes "Following" is what I use. The reason I use it is because of this algorithm that thinks I could possibly want 50% tweets that make me "engaged^H^H^H^H^Hraged". To me, that is a ridiculous mixture.

I'm happy they have a "Following" and I sure hope they keep it, but I will not be surprised if it goes away.

Re: Twitter's Recommendation Algorithm

#559

Post by zeven7 »

eldritch_4ier wrote: post #529
panarky wrote: post #512

Earlier quoted context omitted.

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

[flagged]

I clicked downvote before reading the whole comment. At first I thought you were talking about the red team when you started with "mass riots and violence..." Then I read the rest of your comment and still felt just as good about my downvote. This isn't a constructive comment no matter what "side" you're on.

Re: Twitter's Recommendation Algorithm

#560

Post by regularjack »

eldritch_4ier wrote: post #529
panarky wrote: post #512

Earlier quoted context omitted.

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

[flagged]

"approved terminology".
Post reply on HN