Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

YouTube’s ‘dislike’ barely works according to new study on recommendations

engadget.com

Post reply on HN
Print view View original

381–390 of 437 posts

Re: YouTube’s ‘dislike’ barely works according to new study on recommendations

#381

Post by JohnFen »

brezelgoring wrote: post #193
throwaway2037 wrote: post #137

Earlier quoted context omitted.

This sounds interesting. I tried to Google about it, but I found nothing. How did you learn about this?

I don't know how you can reach it from within YT itself, but I know that if you do a datadump of your account, you can see it in one of the text files within. It, unsurprisingly, has a history of _lots_ of different things, you'll be shocked about how much Google knows about you. Probably things you yourself have forgotten.

That's why although I do subscribe to YouTube Premium (the only Google service I still use), I only use it from an account that is not used for anything else, on a single tablet that is not used for anything else, and pay with a card that is not used for anything else.

Re: YouTube’s ‘dislike’ barely works according to new study on recommendations

#382

Post by JohnFen »

harry8 wrote: post #94
throw_m239339 wrote: post #59

Earlier quoted context omitted.

> Some might say that you can still use search, but that has been crippled to include unrelated recommendations after one page of results. Not only that, I want YouTube to help me discover new content. When the recommendation system works and it shows me new kinds of interesting stuff, it's superb. TikTok is eating YouTube's lunch in this regard. this and it's going too far, since Youtube is now polluting people's se…

Google have a ton of other ML features about you that they fit to the model and so you have been profiled to be a bit lecherous.[1] Do you feel good about that? Think how it must feel to be profiled to be a crook or a bad credit risk or something else that actually impacts your life and is false. It's a little worrying. [1] Other people like you like this so it is assumed you do also. Without "lecherous" ever being m…

The one nice thing about Google's ML features is that they're so absolutely terrible that what they think means nothing about you at all.

Re: YouTube’s ‘dislike’ barely works according to new study on recommendations

#383

Post by JohnFen »

agileAlligator wrote: post #246
daveoc64 wrote: post #131

Earlier quoted context omitted.

The problem with the dislike button seems to be that nobody agrees on what it should be used for. In previous HN discussions, it's become apparent that some people use it to say "I am not interested in this video". That is of zero use to other users. The video isn't necessarily bad, it's just on a topic you don't care about. If you are instead using it to mean "this video is factually wrong" or "this video is obnoxio…

The not interested option already exists, it's just buried. Maybe youtube could bring that to the surface..

If, in fact, that option actually does anything. I'm far from sure that it does. It doesn't seem to affect anything for me.

Re: YouTube’s ‘dislike’ barely works according to new study on recommendations

#384

Post by JohnFen »

sircastor wrote: post #235
DiggyJohnson wrote: post #187

Earlier quoted context omitted.

How is this a useful response to the perspective shared in the GP? Even if you don’t use it, it’s still a useful signal. Are you saying this isn’t the case? For example, did you find the dislike ratio to be a misleading signal, when it was around?

I shared to express that it wasn’t a signal universally understood. I never saw the dislike button as anything other than people hating on a video. There’s no context to it. You don’t know if the dislikes are people who don’t like the content or the author or the subject or the channel. In other words, for me it was never a useful signal. It only reflected how terrible the internet can make people behave. I understan…

I found the like/dislike ratio to be very useful, personally. Since it was removed and I have no signal as to whether or not the video is any good, the number of crap videos I end up playing has increased substantially. It's really annoying.

Yes, certain videos would get bombed -- but that, too, tends to be obvious and tells you something useful about the video: namely, that it's controversial in some way.

Re: YouTube’s ‘dislike’ barely works according to new study on recommendations

#385

Post by JohnFen »

judge2020 wrote: post #63
bobbylarrybobby wrote: post #52

Earlier quoted context omitted.

Isn't it fair that if every player you play against decides they don't want to play with you, you shouldn't get to play? Obviously something is wrong with you. (A 4chan style let's-make-this-person's-life-hell attack notwithstanding)

It wasn't that this player was disrespectful/racist/etc., it's that they were so much better that playing against this player was almost a guaranteed loss.

That sounds like a valid reason to avoid playing against that player.

Re: YouTube’s ‘dislike’ barely works according to new study on recommendations

#386

Post by JohnFen »

adamdusty wrote: post #79
amatecha wrote: post #19

This reminds me of how games ( cough LeagueOfLegends cough ) match me up with a player that I literally just reported for harassment, griefing etc. in the previous match. Like, there weren't any other possible players to match me with out of the many thousands? I don't mind waiting a few more seconds to match up with someone else! I'm getting a lot of responses as if I expect the player to be totally blocked from mat…

This has been discussed by the community for as long as I've been playing (2012ish), and rito has said they won't do it because it creates a "prisoners island" type situation where all the mean players end up playing together and player retention drops. They argue its much better to attempt to rehabilitate rude players, but this was back when riot Lyte was doing his thing. I don't know if they spoken on the subject s…

> They argue its much better to attempt to rehabilitate rude players

That's fascinating. It was rude and nasty players that drove me away from online gaming completely. They make it seriously unfun, and if it's not fun, there's no point in doing it.

Re: YouTube’s ‘dislike’ barely works according to new study on recommendations

#387

Post by JohnFen »

johnfn wrote: post #67
sph wrote: post #17

Earlier quoted context omitted.

YouTube absolutely IGNORES your preferences. I watch it daily, I have never listened to any hip hop, I don't watch sports nor trending topics, yet every single day it suggests football videos, MMA, the latest hiphop hit, and celebrity crap (imagine the Kardashians) among my other interests. I click "don't recommend this channel", or "I don't like this video " every single day, I have an extension to make this conveni…

> I watch it daily, I have never listened to any hip hop, I don't watch sports nor trending topics, yet every single day it suggests football videos, MMA, the latest hiphop hit, and celebrity crap (imagine the Kardashians) among my other interests. I don't have this experience at all. YouTube recommends me pretty much exactly what I've been recently watching. I watch a lot of long form interviews and tech videos, and…

> I wonder if something is wrong with your account?

If so, the same thing is wrong with my account, and that of my other friends who watch YouTube often.

Re: YouTube’s ‘dislike’ barely works according to new study on recommendations

#388

Post by robswc »

cruano wrote: post #361
robswc wrote: post #96

Honestly, I feel like YouTube recommendation is the _only_ good thing YouTube has lol. I often see a ton of complaints about the recommendations but I've honestly never had an issue. I know that yes, you click on one video and now all the sudden you get 100s of that type... but it sorta works for me since it seems like that "effect" wears off just as fast as it starts. For example, I have a friend that's into cars. I…

But just look at that same behavior over time. Say you searched for car videos yesterday, and today you are searching for basketball videos. Old youtube used to be very simple and recommend similar videos to the current thing you are watching, so you would get basketball videos when you were looking for basketball videos. Now, it will do that for some but also put car videos in the recommendations as stuff you "might…

Interesting...

I can't say I've seen this type of recommendation behavior but I totally believe it.

The recommending the same video twice seems like such an easy problem to solve too...

Re: YouTube’s ‘dislike’ barely works according to new study on recommendations

#389

Post by JohnFen »

sph wrote: post #287
johnfn wrote: post #67

Earlier quoted context omitted.

> I watch it daily, I have never listened to any hip hop, I don't watch sports nor trending topics, yet every single day it suggests football videos, MMA, the latest hiphop hit, and celebrity crap (imagine the Kardashians) among my other interests. I don't have this experience at all. YouTube recommends me pretty much exactly what I've been recently watching. I watch a lot of long form interviews and tech videos, and…

> YouTube recommends me pretty much exactly what I've been recently watching. It depends. Maybe I wasn't clear, most of the recommendations are fine (not great, but still pertinent), but sections like "New to you", or "Just uploaded" or even the search suggestions are full of trending videos that I keep telling it I don't care about. Right now I just get recommended three categories of videos: - 90% relevant to my in…

> sections like "New to you", or "Just uploaded"

I actually expect those sections to completely ignore your preferences. They're just advertising sections, so they reflect what YouTube wants you to watch.

Re: YouTube’s ‘dislike’ barely works according to new study on recommendations

#390

Post by robswc »

sytelus wrote: post #267
robswc wrote: post #96

Honestly, I feel like YouTube recommendation is the _only_ good thing YouTube has lol. I often see a ton of complaints about the recommendations but I've honestly never had an issue. I know that yes, you click on one video and now all the sudden you get 100s of that type... but it sorta works for me since it seems like that "effect" wears off just as fast as it starts. For example, I have a friend that's into cars. I…

Most people don’t understand here that folks at YouTube have probably ran thousands of variations of their algorithms and their current system is likely the best yet for keeping highest engagement on average . The issue might be that majority of the population might love recency bias. Folks here are not representative of general pop but they get overrun by majority preferences.

Really good point. It seems like some people do get stuck with a really bad variation and are justifiably vocal about how bad it is.

Perhaps one day everyone could compare and see if it really is just preference or that some people have something gone terribly wrong.

I will admit, I usually see more tech-oriented people complain about it.

Post reply on HN