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 Lemmy 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.
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.
I did take Algorithms.
The definition we learned (let me know if I am wrong) is that an algorithm is a concrete set of steps to accomplish some goal in a finite amount of time given legitimate inputs.
Although in practice we use this more for stuff with a math formula and/or stuff you code. āGiven the input of the world, if your eyes see it is raining outside, grab the umbrella from your closet. If you donāt see the umbrella, search for it. If the search takes 5+ minutes, just go to your destinationā is an algorithm for trying to not get rained on, but in practice nobodyās going to be using that word that way.
I think the definition used online today is āsome computer code that I canāt reliably determine the input/output of, that is used to my/societyās disadvantage in an exploitative way.ā
Words evolve, and the word you learn in academia sometimes also gets used in real life and its usage changes in real life from what you would use in academia. And sometimes academia keeps using it that way, and real life keeps using it their different way, and so you use the same word while talking about slightly different concepts. And sometimes people in real life use it the academic way, others donāt, making things even more confusingā¦ you just have to be aware people are using the same word to talk about two different things (or in this case, one group uses the word to talk about an unpleasant subset of the thing the other group uses the word to talk about) and clear up that misunderstanding.
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.