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

Re:YouTube’s ‘dislike’ barely works according to new study o... by qwertox on Wednesday September 21, 2022 @03:13AM (#32921719)

Apparently you cared enough about it to start watching it after reading the title. A video with "Rust" and "Tokio" in the title will probably be unwatchable if it has a like to dislike ratio of 1 to 3, even if the title signals you that you want to see that video. But since there no longer exists this ratio, you'll have to watch it partially only to notice that it is bad. And then dislike it (and then have this dislike action have no effect whatsoever in future recommendations, apparently).

I absolutely hate it that they removed the dislike counter, it was so valuable.

[ Parent | on HN ]

[dead]

Re:YouTube’s ‘dislike’ barely works according to new study o... by praestigiare on Wednesday September 21, 2022 @06:02AM (#32922856)

I don't know what you think the decision making process was on that, but you're wrong.

[ Parent | on HN ]

Re:YouTube’s ‘dislike’ barely works according to new study o... by friendzis on Wednesday September 21, 2022 @07:52AM (#32923721)

Such decisions are not made on one single metric. these are multi faceted decisions.

Could dislike counts/ratios per like/view/minute been part of the decision? Absolutely. Did certain topics were worse than others? Again, yes.

Is this a whole story? No. Could this have been part of the decision process? It would be hard to convince me it wasn't at least due to human nature.

[ Parent | on HN ]

Re:YouTube’s ‘dislike’ barely works according to new study o... by john_alan on Wednesday September 21, 2022 @07:31AM (#32923553)

OK thanks for the clarity.

[ Parent | on HN ]