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

251–260 of 1001 posts

Re: Twitter's Recommendation Algorithm

#251

Post by smegger001 »

6nf wrote: post #54
jawns wrote: post #31

Earlier quoted context omitted.

The author_is_elon flag doesn't surprise me, but the two political designators are somewhat shocking. I'd sure like to know what changes based on what Twitter knows about your political affiliation.

So many questions. How are users tagged D or R? Is that a manual process or automated somehow? What is the effect of these tags? Can I find out if my Twitter account is in one of those buckets?

you could probably algorithmically determine it in most cases based on any number of indicators from phrases used, to communities interacted with, which hashtages are included, which cohort retweets and likes most etc... thats not even getting into simply tagging political figures with the party they officially affiliate themselves with

Re: Twitter's Recommendation Algorithm

#252

Post by cubefox »

capableweb wrote: post #26

I'm no fan of either Twitter nor Elon Musk, but this is a great move and I hope other companies follow what Twitter did here and start open sourcing more core parts like this. Maybe it's mostly useful for learning how it works, not for directly using it in your own product, but the amount of transparency it gives users cannot be understated. As long as that actually is the code they run, but there would be no way for…

I think it mainly helps with accountability regarding free speech. They did and do several kinds of shadow banning and down-boosting to combat spammers, which always has some false positives. If you the algorithm is published, you could at least better judge and argue when you are unfairly "silenced". Since this may be due to an avoidable flaw of the algorithm instead of some accepted collateral damage.

Re: Twitter's Recommendation Algorithm

#254

Post by lhnz »

photochemsyn wrote: post #205

I generally have a very low opinion of social media platforms, but I did create a Twitter account for the first time after Musk bought the platform. My conclusion is that it's basically entertainment, with very little of what I'd call high-quality useful information that deserves further examination (unlike a lot of HN posts, in contrast). I also notice something of a Tik-Tok approach to video being implemented, whic…

You can follow accounts that only post arxiv.org links for ML papers or anything else you're interested in if you want to. If you're only getting entertainment then it says a lot about the original accounts you followed.

Re: Twitter's Recommendation Algorithm

#256

Post by robopsychology »

jonathanmayer wrote: post #45

Context: 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…

[flagged]

Re: Twitter's Recommendation Algorithm

#257

Post by w0m »

meghan_rain wrote: post #106
jonathanmayer wrote: post #45

Context: 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…

So why did they opensource it?

PR and it was already leaked last week.

Re: Twitter's Recommendation Algorithm

#258

Post by progmetaldev »

Laaas wrote: post #134
dmonitor wrote: post #110

Earlier quoted context omitted.

immediately getting rid of the sparkle button is one of the few reasons i still have a small amount of faith in elon’s vision of twitter

- 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.

Not having to login to Twitter is a great feature. I don't have a Twitter account, but often see posts linked elsewhere, and hated getting hit to login each time.

Re: Twitter's Recommendation Algorithm

#260

Post by TaylorAlexander »

Laaas wrote: post #134
dmonitor wrote: post #110

Earlier quoted context omitted.

immediately getting rid of the sparkle button is one of the few reasons i still have a small amount of faith in elon’s vision of twitter

- 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.

The spam comment is interesting. I had a sharp uptick in the number of spam messages after the acquisition.
Post reply on HN