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

891–900 of 1001 posts

Re: Twitter's Recommendation Algorithm

#891

Post by prezjordan »

lenkite wrote: post #714
slg wrote: post #658

Earlier quoted context omitted.

This shouldn't really be a surprise to anyone. It was reported years ago that Twitter was unable to cut down on hate speech because the automated systems they developed triggered too many [debatably false] positives on Republican politicians and that was bad for the company's reputation. If Twitter wanted to prevent future code changes from impacting that approach, there needed to be something like this in the code o…

[flagged]

This is a lie. We got a glimpse into how accounts like LibsOfTikTok regularly set off alarms only to get tags such as "Do not ban. Ask first."

The only thing selective and explicit was the information Musk allowed bought-and-paid-for "journalists" to access.

Re: Twitter's Recommendation Algorithm

#892

Post by dbbk »

airstrike wrote: post #451
jandrese wrote: post #373

Earlier quoted context omitted.

I thought it was interesting how it explicitly doesn't boost independents. So much of the two-party system is self-reinforcing.

Also how about.... everyone else in the world who is not an American voter?

This is an interesting point... they're making sure their A/B experiments don't adversely affect Republicans or Democrats. But lots of European countries are skewed more to the left and would broadly look more similar to the "Democrats" group.

Re: Twitter's Recommendation Algorithm

#893

Post by dbbk »

fknorangesite wrote: post #696
coolspot wrote: post #589

Earlier quoted context omitted.

BTW: How @aoc got three-letter handle?

Probably exactly the most boring, mundane way you would expect: they managed to contact the owner of what was probably a dead/inactive account and then paid them some money for it.

It's against the Twitter terms to pay money for accounts. I think more likely is that Twitter 'seized' the dead account and just granted it to her. I'm sure for instance someone had previously squatted on accounts like "VP" or "England"

Re: Twitter's Recommendation Algorithm

#895

Post by dbbk »

Joeri wrote: post #777
smt88 wrote: post #477

Earlier quoted context omitted.

This is transparency theatre, not actual transparency. There's no way to actually use this limited release to understand how or why any tweet is boosted, so we're in exactly the same boat we were in yesterday.

I did find the article more enlightening than the source code. I always suspected the quality of a tweet did not factor in to its promotion, only its engagement, and now they have confirmed this to be the case. Now I understand better why twitter seems to be filled with people angrily retweeting what I consider to be low quality clickbait tweets. As long as they don’t try to tackle tweet quality at all separately fro…

"Quality of a tweet" is impossible for a computer to understand. That's like asking to quantify the value of a work of art just from the image.

Re: Twitter's Recommendation Algorithm

#896

Post by anyonecancode »

OJFord wrote: post #689
SequoiaHope wrote: post #211

Earlier quoted context omitted.

Well if they say “we will open source the algorithm” and then what they really open source is a little bit of slightly relevant code that doesn’t allow us to understand the algorithm, then what we can deduce is that they are trying to weasel out of public commitments. I can’t say for sure if that happened, but if they made a clear promise and then did something else, it’s perfectly reasonable to call that out.

Devil's advocate though: imagine you were to open source (probably with quite a short deadline) some 'algorithm' used in whatever you work on, but the rest should stay private; how would you go about that? I don't think it's easy, there's inherently some interface(s!) where it's a hand-wavey 'get the thing from the private bit', and defining that sensibly is hard, and if you try to do it well will probably lead to a…

It depends on what your goal in open sourcing is. Are you looking to provide a base for others to build software on, and to provide a way for others to contribute back to your code? Then publishing the code makes sense.

Are you looking to build public trust in you and your organization? Then dumping a bunch of code with no context isn't going to help much, as it's not code but behavior that builds or destroys trust.

Are you looking to lean into a polarized partisan environment, pushing a narrative where its you and your supporters against an unfair group of "others"? Then a big splashy move high on symbolism and low on substance that will inspire lots of high profile, divisive media coverage is a great way to go.

Re: Twitter's Recommendation Algorithm

#897

Post by dbbk »

corbulo wrote: post #181
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.

I'm confused, then why not just use your 'followed' feed instead of 'for you'?

Because the Followed feed is purely chronological. An interesting tweet from someone I follow could have happened 3 hours before I opened the app, and I would miss it.

This is why I preferred the old For You tab - it was (mostly) the people I had chosen to follow, but meant that I had the best content show up whatever time of day I opened the app. This is particularly important when I'm in the UK and most of the people I follow are in the US, so they're not tweeting generally at the same time I'm on the app.

Re: Twitter's Recommendation Algorithm

#898

Post by dbbk »

jeffbee wrote: post #92

Why does anyone use "for you"?

Because I'm not on Twitter 24 hours a day. I want a recap of the best stuff that's happened since I last opened it. If I use the Following tab, I'm only getting the realtime firehose, meaning if the best stuff happened an hour ago I'd miss it.

Re: Twitter's Recommendation Algorithm

#899

Post by yreg »

thefreeman wrote: post #249
alfor wrote: post #122

Earlier quoted context omitted.

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".

If you don't care whether the content is generated then you don't need to use a social network at all. GPT can generate you an endless interesting feed no problem.

Re: Twitter's Recommendation Algorithm

#900

Post by yeahsure22 »

ModernMech wrote: post #882
concordDance wrote: post #846

Earlier quoted context omitted.

I don't see an unbiased way to tell which "side" releases more disinformation and incitement to violence. Even deciding what counts as disinformation is hard (e.g. does it have to be literally false or just cause false beliefs in the reader?).

One way to tell would be to look at which side is incited to violence more often. It turns out, according to the FBI (which is a conservative organization historically and exclusively run by conservatives), right wing extremism and violence is in fact the biggest domestic terror threat in the US, and it's currently growing [1]. FBI Director Wray gave this testimony after a right wing domestic terror attack was carrie…

[dead]
Post reply on HN