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

71–80 of 437 posts

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

#71

Post by null0pointer »

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…

I've noticed this happen in other online games. So these days when there's someone I don't want to play with again I will report them but also wait a few minutes before queuing for the next match to give that player time to get matched with others.

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

#72

Post by mod »

PaulHoule wrote: post #3

It’s been a while since I’ve logged into YouTube but my impression is that the experience including recommendations is worse if you are logged in.

I absolutely do not agree. I have some kind of legacy "youtube" account, which is not a google account. When I occasionally get switched to my Google account, which does not have my YT history of views/likes/etc, I get tremendously bad recommendations. Just the biggest youtubers with the most click-baity titles, and topics like celebrities, which I actively hate.

Also I find it gives me a ton of recommendations for videos I've already seen.

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

#73

Post by hiimshort »

washywashy wrote: post #66

I attended a conference a few years back where a lead ML/data scientist at a big company you’ve heard of and probably use said the dislike button was ignored in favor of this: did you watch and engage with the content.

This lines up with my experience and continued frustration with YouTube. I use the service a lot whether it be for background noise, research, and so on. The recommendations have been awful (doubly so in Shorts) regardless of how many videos I dislike or categories of channels I choose to stop recommendations of.

My only question then is: how do I know if I dislike a video if I haven't watched it? Sometimes I can leave a video early, but others I will have to watch for a bit before realizing it is a waste of time. This is more pronounced with Shorts due to the duration of videos. I will end up watching something that is 20 seconds long to see what it was about (you never know when you will find a gem), but then dislike it once it is finished. YouTube just keeps recommending low quality garbage until I get fed up with it and spam "Do not recommend channel" the moment a video shows up.

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

#74

Post by dpkirchner »

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.

Wouldn't a good skill based matchmaking system take care of that?

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

#76

Post by ketzo »

dpkirchner wrote: post #74
judge2020 wrote: post #63

Earlier quoted context omitted.

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.

Wouldn't a good skill based matchmaking system take care of that?

That’s the problem.

this player was at the top of the matchmaking ladder

that (very small) population had a lot of people who wanted to avoid him

he couldn’t get games at his current level, and he couldn’t rise above that level, because there was nothing above that level

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

#77

Post by londons_explore »

Long ago, tech giant CEO's realised that recommendation systems are very powerful. They can trick hundreds of millions of users into spending double digit percentages of their life watching memes.

From that point on, focus was reduced on working on recommenders. Instead the goal was not to trick users into spending their whole life on the platform, but to maximize ad revenue from those users in the limited time they did spend on the platform.

The one party that wasn't part of this was tiktok. And that's why they have stolen so much user share.

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

#79

Post by adamdusty »

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 since.

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

#80

Post by mikrl »

I didn’t like when they removed the dislike counts, and I still don’t like it.

When I look for videos of folks working on Subarus, I don’t want to have to manually scrub through the video to gauge the quality. Before I’d just look at the ratio and if I was feeling generous I’d preview the frames to see if they had what I wanted.

Now it takes me at least 2 mins longer to get to the same judgement which begs the question of why I’m watching a video when I have a book on my lap and a car waiting outside.

Post reply on HN