“Twitter has an algorithm that creates harassment all by itself” • Hacker News Board

Re: “Twitter has an algorithm that creates harassment all by itself”

#21

Post by izzydata » Wed, Jun 26, 2019, 8:39 PM UTC

wmil wrote: post #17

lilbobbytables wrote: post #6

"Twitter has an algorithm that creates harassment all by itself" What am I missing here? There was no harassment of any sort. Alternative headlines could have been: "Twitter has an algorithm that helps you gain more followers" "Twitter has an algorithm that helps you drive awareness" "Twitter has an algorithm that helps you get more twitter followers for your cause or business" "Twitter has an algorithm that expands…

I guess the point is that Twitter could easily tone down pile ons by noticing that a tweet is generating many more replies than likes. Then reduce display of that tweet instead of boosting it to non-followers. Perhaps not for blue checkmarks (they've declared themselves central to the public debate), but for average users Twitter should try to calm down pile ons.

That doesn't sound like a solid indicator of an issue. Two friends could be having a back and forth discussion with no harassment or conflict. You'd end up with 25+ replies and 1 like.

Re: “Twitter has an algorithm that creates harassment all by itself”

#22

Post by MBCook » Wed, Jun 26, 2019, 8:41 PM UTC

izzydata wrote: post #21

wmil wrote: post #17

Earlier quoted context omitted.

I guess the point is that Twitter could easily tone down pile ons by noticing that a tweet is generating many more replies than likes. Then reduce display of that tweet instead of boosting it to non-followers. Perhaps not for blue checkmarks (they've declared themselves central to the public debate), but for average users Twitter should try to calm down pile ons.

That doesn't sound like a solid indicator of an issue. Two friends could be having a back and forth discussion with no harassment or conflict. You'd end up with 25+ replies and 1 like.

That would only be two people. You could factor in # of users.

Re: “Twitter has an algorithm that creates harassment all by itself”

#23

Post by nerdponx » Wed, Jun 26, 2019, 8:41 PM UTC

amatecha wrote: post #4

Yeah, this has been a pretty obvious change in the recent months/years. I started noticing tweets in my timeline that were there because it was something someone I follow had replied to -- and these tweets were often "outrage-worthy" or otherwise click/flame-bait. I have since written my own Chrome extension to hide all "suggested" tweets of that sort (as well as hiding all sponsored tweets, and the "Favorite" button…

They probably have some kind of text classifier that's trained on `tweet_contents -> engagement`, with some suitable engagement metric (dwell time, likes, replies, etc).

Re: “Twitter has an algorithm that creates harassment all by itself”

#24

Post by moorhosj » Wed, Jun 26, 2019, 8:43 PM UTC

izzydata wrote: post #21

wmil wrote: post #17

Earlier quoted context omitted.

I guess the point is that Twitter could easily tone down pile ons by noticing that a tweet is generating many more replies than likes. Then reduce display of that tweet instead of boosting it to non-followers. Perhaps not for blue checkmarks (they've declared themselves central to the public debate), but for average users Twitter should try to calm down pile ons.

That doesn't sound like a solid indicator of an issue. Two friends could be having a back and forth discussion with no harassment or conflict. You'd end up with 25+ replies and 1 like.

You could simply add the number of distinct users replying. Seems like a pretty simple fix.

Re: “Twitter has an algorithm that creates harassment all by itself”

#25

Post by shakyshakyshaky » Wed, Jun 26, 2019, 8:44 PM UTC

MBCook wrote: post #22

izzydata wrote: post #21

Earlier quoted context omitted.

That doesn't sound like a solid indicator of an issue. Two friends could be having a back and forth discussion with no harassment or conflict. You'd end up with 25+ replies and 1 like.

That would only be two people. You could factor in # of users.

additionally, there's no real need for technically public discussions to be promoted or made more public, so it's not really a failure state if the algorithm doesn't promote a high reply rate exchange between two users exclusively.

Re: “Twitter has an algorithm that creates harassment all by itself”

#26

Post by ASalazarMX » Wed, Jun 26, 2019, 8:45 PM UTC

freehunter wrote: post #7

My business does a lot of posting on Facebook of sometimes controversial things (we're a news site and we sometimes cover local politics). By far the most engaged stuff is the most controversial where people begin to fight and attack each other. I have ~3k followers on one of my pages. Usually ~200-300 people see any given post if it has no engagements. If it has normal engagement, it might get to 1000-2000 views, st…

> By far the most engaged stuff is the most controversial where people begin to fight and attack each other.

Well, duh. If people are fighting they are definitely "engaged", but not in a good way. Defining that more engagement equals more success is what made social networks so toxic. The current state that more eyeballs equals more ad money needs to change.

Re: “Twitter has an algorithm that creates harassment all by itself”

#27

Post by izzydata » Wed, Jun 26, 2019, 8:48 PM UTC

moorhosj wrote: post #24

izzydata wrote: post #21

Earlier quoted context omitted.

That doesn't sound like a solid indicator of an issue. Two friends could be having a back and forth discussion with no harassment or conflict. You'd end up with 25+ replies and 1 like.

You could simply add the number of distinct users replying. Seems like a pretty simple fix.

I'm still not very convinced that replying without liking is an indicator of negativity. Maybe in most cases, but definitely not all cases.

I don't use the like feature on the website at all and often comment on artwork saying how nice it is or whatever.

Re: “Twitter has an algorithm that creates harassment all by itself”

#28

Post by kevingadd » Wed, Jun 26, 2019, 8:54 PM UTC

jd_nlp wrote: post #20

lilbobbytables wrote: post #6

"Twitter has an algorithm that creates harassment all by itself" What am I missing here? There was no harassment of any sort. Alternative headlines could have been: "Twitter has an algorithm that helps you gain more followers" "Twitter has an algorithm that helps you drive awareness" "Twitter has an algorithm that helps you get more twitter followers for your cause or business" "Twitter has an algorithm that expands…

I can see the poster's point of how it could lead to negativity in some cases, but like you I don't understand what the big revelation is here. Social networks thrive off more people interacting with more posts, so they show posts that have been interacted with a little bit to lots of people hoping they continue to get interacted with. That doesn't really surprise me at all.

The idea of twitter just randomly deciding to boost a low-like-count tweet because it got replies is EXTREMELY WEIRD. Nobody knew the service worked this way. Showing friends' likes in your timeline is not a new deal but in this case there weren't likes, it was just "high engagement". High engagement tweets are often controversial posts from women or conservatives or leftists, and all of those groups are likely to get inflammatory replies that the original poster may not have wanted - you don't have any control over whether your tweet goes viral or gets ratioed.

Re: “Twitter has an algorithm that creates harassment all by itself”

#29

Post by kevingadd » Wed, Jun 26, 2019, 8:55 PM UTC

numbers wrote: post #11

It might be just me but wow, it's really hard to read multiple tweets as a timeline since I don't know where to start and where to end.

This is because they broke threading and the replies section for a tweet now shows parent tweets. It's bizarre, and twitter breaks the replies view on a regular basis and only notices weeks later. It's not just you.

Re: “Twitter has an algorithm that creates harassment all by itself”

#30

Post by freehunter » Wed, Jun 26, 2019, 8:57 PM UTC

izzydata wrote: post #21

wmil wrote: post #17

Earlier quoted context omitted.

I guess the point is that Twitter could easily tone down pile ons by noticing that a tweet is generating many more replies than likes. Then reduce display of that tweet instead of boosting it to non-followers. Perhaps not for blue checkmarks (they've declared themselves central to the public debate), but for average users Twitter should try to calm down pile ons.

That doesn't sound like a solid indicator of an issue. Two friends could be having a back and forth discussion with no harassment or conflict. You'd end up with 25+ replies and 1 like.

What's the point of locating in Silicon Valley and hiring the smartest programmers in the world if you can't figure out an algorithm to make hateful posts not show up as often in someone's feed?

I doubt it's because they can't. The more likely answer is they don't want to.