No matter which sort you use (except for new), content is recommended to you by activity. Depending on the sort (active, hot, top) it uses a slightly different mixture of votes/comments/time since post to determine the order.
The only exception is scaled, which boosts a little bit midsized communities, but still doesnāt manage to improve visibility of niche ones.
If lemmy is to truly start having active hobbyist communities instead of being 95% lefty US politics, Shitposts, and some tech stuff, it needs a sort that takes into account the userās engagement.
For example, if I upvote / comment often in a community, there should be an option to have posts from the community be boosted in my feed, even if itās a tiny community.
Letās say Iām subscribed to !world@lemmy.world and !news@lemmy.world because I want to occasionally see news. However, Iām also subscribed to a couple hundred other communities, some of them who donāt manage to get more than a couple upvotes on their biggest posts. And whenever I see them Iām replying/upvoting because Iām passionate about that topic.
My feed shouldnāt be 95% c/news and c/world because those are the most upvoted and commented. I shouldnāt have to scroll down hundreds of posts to find ābigā posts in small communities I interact with at any opportunity I get.
Thatās why I think it would be beneficial to lemmy if the sort/algorithm took into account your engagement in a way.
It doesnāt have to be complicated, you can have a single number āengagement scoreā for every community calculated with a basic formula, and that number is used as a boost to the community.
Iām aware that there are some examples of successful niche communities on lemmy. But thatās mainly because either a significant chunk of the lemmy userbase is into that niche (letās face it the lemmy community is not a representative sample of the world population, we tend to be very similar people), or because the posts on it are simplified image/video type posts which appeal to people who donāt know much about the subject.
Nah. Algorithms, especially personalized as a way of sorting a feed are just a shite idea. Maybe one of the iOS apps will add something like that but if anything is being different is a selling point. I got two friends on fedi by telling them that āit has no algorithmā which is a simplification of course but you get the gist. It also really hits home that this is not a corporate product.
Algorithms are fine when an algorithm is open, clear and optional. The default sort for many apps/UI is āActiveā, thatās an algorithm. It may be a simple one, but itās an algorithm.
When do you start counting it as an algoritm.
The current sorts (except new) are based on formulas, does suddenly adding a personal engagement variable into the formula make it an algorithm?
Itās arbitrary but something like
SELECT * FROM posts WHERE datePosted < ( currentDay() - 7) ORDER BY upvotes;doesnāt feel like an algorithm as it is now used in common parlance to me.A simple quantitative analysis of an existing metric and (upvotes in the above super simplified example) is just not really the same thing in practice as say: multiple linear regression of hidden backend engagement metrics gathered through things like cursor movements to pick a suggested video that is predicted to optimize the best for watch time and CTR from a list of videos on a balance of personalized and generalized (through tracking trends amongst demographics) favourites topics and other qualities classified and categorised by a whole other black box involving all sorts of classifier models from text to images and so on.
Idk, I didnāt take algorithms in CS at uni, so this is just a laymanās two cents. Iām happy to be explained to why this isnāt a valid perspective.