YouTube’s ‘dislike’ barely works according to new study on recommendations
191–200 of 437 posts
Re: YouTube’s ‘dislike’ barely works according to new study on recommendations
#192I 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 questi…
> Now it takes me at least 2 mins longer to get to the same judgement
Sounds like metrics at work.
Re: YouTube’s ‘dislike’ barely works according to new study on recommendations
#193Earlier quoted context omitted.
YT has hidden tags that tie it to your account after viewing a video, removing the video from played/history does not affect this and has been an issue with YT for nearly 6-7 years at this point.
This sounds interesting. I tried to Google about it, but I found nothing. How did you learn about this?
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.
Re: YouTube’s ‘dislike’ barely works according to new study on recommendations
#194Honestly, 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…
Completely disagree. I think what is great about YouTube are the subset of creators that make genuinely good content, and especially those creators you follow consistently for a long time and really enjoy and get something out of. The algos are useful if I follow so many creators that I can’t keep up, or occasionally I get some good unexpected content. But my favorite creators were all recommended me by other people,…
Very odd and you can certainly get some bad content in the mix because they don't know what they're doing.
Re: YouTube’s ‘dislike’ barely works according to new study on recommendations
#195Earlier quoted context omitted.
I've had videos not show up in the YouTube search despite the query matching the video title verbatim.
Prepend your search with 'intitle:' and you'll get results with the string in the title.
Re: YouTube’s ‘dislike’ barely works according to new study on recommendations
#196Honestly, 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…
Not sure what we are doing differently but for me it's pretty much random and useless. It seems to be a mix of mostly old videos from channels I follow anyway and random junk I am not interested in. I am sure I could find something new and interesting in there if I looked long enough but the signal/noise ratio is very low. Old account with thousands of views and likes/dislikes.
Re: YouTube’s ‘dislike’ barely works according to new study on recommendations
#197Honestly, 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…
There is some incentive to want you to watch car videos in that situation, as someone with a recent automotive interest is an ideal person to show car ads to.
Another example though... I just watched a few videos about fake self help gurus and influencers. I now have 3/10 recommended videos about that. 2/10 a random meme (which do look funny, tbf) and then the rest are subs.
Re: YouTube’s ‘dislike’ barely works according to new study on recommendations
#198Re: YouTube’s ‘dislike’ barely works according to new study on recommendations
#199The trick to improving YouTube recommendations is to regularly prune uninteresting videos and channels. Eventually this should start surfacing videos you're more likely to find interesting. I've actually hit the end of my recommendation stream on the mobile app after marking dozens of videos with Not Interested. Once this happens it starts recommending videos you've already watched or older videos from creators you'v…
The biggest problem with this approach is that it takes a lot of curation to get your recommendation in a decent shape and it takes you one accidental video view to have your feed be full of uninteresting content related to that video. This asymmetry is the root of all the recommendation system problems.
It seems like the problem of asymmetry in recommendation platforms is more a choice from a design perspective than a challenge yet to be figured out.
I'm far from an expert tho so just a thought from a laymen
Re: YouTube’s ‘dislike’ barely works according to new study on recommendations
#200The trick to improving YouTube recommendations is to regularly prune uninteresting videos and channels. Eventually this should start surfacing videos you're more likely to find interesting. I've actually hit the end of my recommendation stream on the mobile app after marking dozens of videos with Not Interested. Once this happens it starts recommending videos you've already watched or older videos from creators you'v…