view the rest of the comments
Ask Lemmy
A Fediverse community for open-ended, thought provoking questions
Please don't post about US Politics. If you need to do this, try !politicaldiscussion@lemmy.world
Rules: (interactive)
1) Be nice and; have fun
Doxxing, trolling, sealioning, racism, and toxicity are not welcomed in AskLemmy. Remember what your mother said: if you can't say something nice, don't say anything at all. In addition, the site-wide Lemmy.world terms of service also apply here. Please familiarize yourself with them
2) All posts must end with a '?'
This is sort of like Jeopardy. Please phrase all post titles in the form of a proper question ending with ?
3) No spam
Please do not flood the community with nonsense. Actual suspected spammers will be banned on site. No astroturfing.
4) NSFW is okay, within reason
Just remember to tag posts with either a content warning or a [NSFW] tag. Overtly sexual posts are not allowed, please direct them to either !asklemmyafterdark@lemmy.world or !asklemmynsfw@lemmynsfw.com.
NSFW comments should be restricted to posts tagged [NSFW].
5) This is not a support community.
It is not a place for 'how do I?', type questions.
If you have any questions regarding the site itself or would like to report a community, please direct them to Lemmy.world Support or email info@lemmy.world. For other questions check our partnered communities list, or use the search function.
Reminder: The terms of service apply here too.
Partnered Communities:
Logo design credit goes to: tubbadu
I disagree entirely.
I used the free trial. The algorithm was a whole lot shittier than spotify's recommendations. It had the same annoying vibe as the regular youtube algo where if you watch one video from Jordan Peterson, you suddenly inherit the feed of an Elon Musk worshipping alt right tech bro.
It was the same for music. I listened to one song as a joke then it stopped recommending good music and just made my whole feed into joke songs. Much like youtube's algorithm, youtube music algo clearly uses google's machnine learning tech (which they use for ads too) where it tries so hard to predict what you like without real data, instead preferring to use solely other people's browsing habits rather than creating a unique profile for that user without it making too many assumptions right off the bat. Perhaps, I'd describe that algorithm as "HIGHLY reductive" when compared to any other recommendatiion algorithm which seem more geared toward slowly discovering the tastes of its users.
This might be a function of low usage time, the shifts were definitely more pronounced in the beginning, now when I listen to new stuff it only introduces the changes in the appropriate mixes (i.e my mix 1-3 is various hiphop (very well segregated into different styles i must add), 4,5 is indie/rock etc) and the amount is a function of how much of said new stuff i listen. On occasion i will use votes and the dislikes especially affect playlists quickly.
I know the youtube behaviour you refer to and it honestly really makes me hate watching youtube, some days I will have a bad mood and start spamming not interested for a few rows and my feed is good again.
But with YTM it seems to be really nice, whereas with spotify, as OP, I found it quite stale.