What other less-toxic system could work instead of karma?

That real question is, what problem are we trying to solve? Then we can go from there.

In wondering about that myself. What is the problem?
- Repetitive low-effort posts and comments were common on Reddit
There are few things Karma system helps with that come to mind.

For others:

Reputation

Activity

For you:

That endorphin XP boost when you level up. Makes you more likely do engage after the first hit.

Gives you an idea how your comment has been received by others.

Presumably there are other things as well, these just quickly came to me.
- That is a good way to think about it. What is the need from the reader's perspective and from the poster's.
  
  One would certainly read a post with low upvotes from a author with high reputation if you are interested in the specific magazine. I wonder if the reputation should not be topic bound and not just general. That would be useful from the reader's perspective.
Number go up, makes brain happy
- Number go down, makes brain sad ;(
The first problem is people tend to follow the hive mind. If it's downvoted, they will also downvote and vice versa. They also will believe a comment with lots of upvotes and won't fact check.

The second problem is people will abuse a karma system. Bots can increase the reputation of an account to make them seem more trustworthy

The third problem is that the current system let's you see who is downvoting/upvoting. People take it personally when they are disagreed with and will retaliate since they can see those users and stalk their account

I don't think these problems warrants a change in the current system. The transparency is a crucial feature. Seeing the number of downvotes serves as a great red flag to warn readers that a comment might not be true even if it has a larger number of upvotes.

This does take away the anonymous part of your social media voting experience, but the ability to manipulate the platform is greatly decreased. People that get riled up about disagreement will need to chill and you will need to block those individuals that can't.

I think this will allow the development of a more mature community by taking away some of the anonymity
- The third problem is that the current system let's you see who is downvoting/upvoting. People take it personally when they are disagreed with and will retaliate since they can see those users and stalk their account
  
  I actually really like this. I've been downvoted a bunch, my kbin karma sits at negative, but it's kinda neat to see that I haven't been downvoted by complete assholes (based on their history) -- makes me appreciate that we might just have different view about a thing (or I've acted like an asshole to no surprise). Nonverbal communication can be a powerful thing.
  
  Do I think it's feasible to leave as it is if this whole thing explodes in popularity in a new magnitude while Reddit sinks? No I don't think so.
Not a problem at all. I understand that we are ego-driven, but then again, the fediverse is a new working paradigm. We are here because we want to. Genuinely curious what you guys thought!
- We want to discuss topics. This is a place to do that.
  
  Simple need, simple solution.
  
  You don't need an extra incentive to make people talk about things if people talking about things is the thing you want. You don't want to incentivize people who don't want to talk about things to be active somewhere you want people to talk about things because then those people will start doing the thing your'e incentivizing them for instead of talk about things.
  
  I personally only want people who want to talk about things here, and don't want people who don't want to talk about things.
Yeah, the question strikes me as, "Reddit has this thing. A lot of people don't like that thing, but how could we still have it without people not liking it?"

I think we're good as is.
I think you're onto something here
Karma already barely matters on Reddit unless it's negative. It's useful in that case because it lets moderators automatically reject membership in a community for people who are overwhelmingly downvoted for contributions.
Good point, take my:

handshake, pat on the back, slightly too long hug point thingy.

What we have right now in Lemmy strikes the current balance IMO. Individual comments are upvoted/downvoted. But no cumulative score.

which is the right thing, judge the opinion not the person
- There is that aspect of karma of "if you've got negative karma, you're probably intolerable" but I'm not sure how much that helps in practice vs just banning people. Karma can also filter out fresh accounts for high spam communities, ofc, that doesn't work perfectly either...
- Agreed 105%
- I agree 90%, downvotes shouldn't have that much weight. That said, comments which are abusive or hateful probably should have long term consequences for the user, even if they are themselves not worthy of a ban. Maybe reputation can be a "strike" for number of reported comments.
  
  To be clear, here I'm thinking of "dogwhistle" comments which individually are plausibly fine, but in aggregate indicate this person is up to no good.
I would almost say a better system would obscure usernames completely. Only show the comment text, and allow voting accordingly.
- No, we need people to have some accountability or everyone's just gonna be intolerable.
- basically 4chan but with extra steps 🤔
- this makes me think of 4chan and i don t think this should be that kind of community
- How will I upvote people for having a name like rimjobsteve or a username related to the context ala r/usernamechecksout! /J
On the other hand, kbin has a cumulative score, but currently implements it badly wrong. Your cumulative 'reputation' is calculated as "boosts - downvotes". So if you post a thread that gets 100 upvotes, 9 downvotes, 80 comments and 5 boosts, you are rewarded with '-4 reputation'. Nobody really uses boost, so it is very easy to rack up negative reputation.

Thankfully, I don't think 'reputation' actually does anything, but it is still kind of annoying to be 'punished' for posting.

I'm against any kind of global user ranking.

It makes sense to rank content, but ranking users just begs abuse of the system. There's always those that will try to farm the system resulting in lower quality content. It's also an attack vector for bots.

I don't miss the "karma" aspect one bit here. Rate my post quality, not me. On the other hand, tools for ranking users privately could be helpful. In other words a personal ranking for your eyes only would be fine.

I agree. I personally found the system was far too addictive, in the Cookie Clicker kind of way of "bigger number = happy". I sometimes find myself missing it almost, only to remember that it's worthless.

It also means I can more freely share my actual opinions, without that reflecting on some sort of global score if people generally dislike said opinion.
- Yes, look up "Facebook demetricator". It was brilliant. I'm glad I never used Facebook.
i do like the RES feature of personal counts though

if someone on res had a [+10] next to their name, i'll know i personally respect their opinions, even if i don't remember their name. similarly, if they have a negative number, i'll know not to engage as they're probably a troll

No system. The goal isn't Reddit 2, it's a federated link aggregator.

fax

I much prefer how Lemmy approaches this; upvote and downvote count per comment, no tally of total points.

Way less people trying to Karma farm then and repost content for fake internet points that don’t mean anything.

Unfortunately, anything you replace karma with will have the same problems that karma has. Any indicator of comment or user quality will be readily gamed by anyone with any skills whatsoever in automation.

Yes and no. Toxicity will always be around indeed... but we can definitely lessen its effect.
thing is... in the end, karma doesn't serve as that anyway (indicator of quality). It's so easy to karma farm by (re)posting content (sometimes even stolen) in multiple communities.

In NSFW communities, at least on Reddit, I see SO MANY posts that doesn't fit the community they were posted in, but being upvoted anyway because... well... it's nudity
- Karma may not be an actual indicator of quality, but it is often used as such. That's the reason why all the bots exist in the first place and they are oddly enough* also the reason it's not a good indicator.
  
  People look at top, People like to filter out the bottom.
  
  Look at the alternatives. Page views? They'd be instantly botted. Engagement? Instantly botted. There's literally not any way to indicate that the crowd likes something or that something is of interest that can't be replicated in a hot second. Karma is the closest thing we have to a sorting filter that content creators are doing the right thing or an indicator to content consumers that something might stand out from the crowd.
  
  I'm sitting here farming /r/interestingasfuck trying to make the /c/interestingasfuck viable and 2/3 of the highest ranked crap is garbage, The thing is, even 1/3 of it being real saves me from having to sort through thousands of page of crap to find decent stuff.
  
  edit* missed a word

We should keep it as is. Having an account score just amplifies a big issue with sm. The content should be in focus, not the people posting. A relevant comment should be hightened because it itself is good. In the same way we shouldn't judge something because the user has a low karma, but because the content is bad.

The idea behind something keeping a score on a profile is good, but it doesn't work as intended in practice. People will farm in whatever way they need to get a moral highground. Not having such a scoring system will be a good way to reduce the incentive to copy/paste content from others.

You said this far better than I could. If there's no supply, the addicts stay away.
A relevant and good comment, even and especially if it opposes the opinion of the majority. Giving downvotes to signal disagreement, when posts are sorted by karma and very low karma posts are even hidden, leads to circle jerking and immediately kills every healthy debate and controversy in the bud. If I have a dissenting opinion, I want to argue, not be muzzled.

What about the same system, but it shows both upvotes and downvotes?

I’d prefer that. 2600 up and 2500 down is really different than 105 up and 5 down
- Tbf you can probably tell the actual numbers by looking at the % reddit shows in the corner, but that's not very intuitive
Yeah imo the real problem with reddit was that

A: they started fudging the votes so they didn't really matter and they could shadowban accounts from even being able to upovte/downvote

B: stupid fucking awards could keep posts at the top even if they had like -2000

c: fascists were gaming the system with bots anyway to push their content.

It’s a shame, but any sort of number-based system will most likely end up with the same problems as karma. Not having the numbers add up is a good start though, since upvotes and downvotes are only really useful as ‘in-the-moment’ indicators of good vs bad content.

Let’s keep it how it is, so that we don’t have another social credits system that doubles as a dopamine factory.

Another element is that total upvotes don't need to be shown on your profile. It can be on the comments/posts alone.
- I like that.

I think we should stop seeing Lemmy as just a substitute for Reddit. Lemmy can be it's own thing, without having to do 'reddit-like' stuff.

Imo, I don't think the karma system is really necessary (it doesn't even make sense) and the upvote-downvote is good enough to filter quality posts.

That is indeed my fault. I came looking for something to end the craving and the void left by reddit. I should rethink my approach and understand that this could go beyond my ego
- This is really a great approach not only to the matter at hand, but to life in general. I wish more people used it in the world.
- Props to you for admitting where you could approach this in a more healthy way. Too few adults seem capable of doing such.

Karma does well in my opinion, however it should display the number of upvotes and downvotes, not just one number. Also adnn an option to sort by the number of downvotes.

And an option to sort by controversial would be nice.

Also add an option to sort by the number of downvotes.

More sorting options would be a nice addition. Although, being able to treat down-votes similarly to upvotes might encourage more bad behavior. I kind of want to see such a system tested.
Trolls would compete to be the worst.
- Let them have their pathetic fun. We're never going to stop trolls, might as well let them get their dumb points while they're at it. It's not like they aren't typically obvious anyway.
- I never though about it, but if people compete to be the best, some others could also compete to be the worst…

Absolutely nothing. Reducing people to a number and ranking their value based on that is inherently wrong.

Keep it simple, the current Lemmy system works fine. Spambots and particularly disruptive people should just be banned anyways, a gamification system would not solve any issue on that front.

But what about the dopamine hit from upvotes though...
- Let's keep the upvotes to the post/comment only, do not show the overall of a user and don't take it into account in any algorithmic decision. Let community managers see the 'karma' of the user in their respective community maybe, but beyond that it's a feature that only had negative implications on Reddit
While I still would like to see an alternative to Karma that's less problematic, I agree with the idea that gamification will not solve issues. If anything, it creates a "KPI/score" people want to desperately meet for the wrong reason.
👍

I don't think you can have anything in the same spirit that isn't toxic and doesn't encourage brigading by minority groups who want to cancel opinions they don't like. The whole concept is simply glorified ad hominem.

Absolutely. The real reason accounts accrue karma on reddit is to keep you engaged. People get addicted to big numbers. It's just toxic. Upvote and downvote posts and comments but don't keep a running tally on people's accounts.
- Do you guys think there could be a different system that could work?

Web of trust. The biggest thing missing from most attempts to build social networks so far. A few sites did very weak versions, like Slashdot/s friend/foe/fan/freak rating system.

Let me subscribe, upvote, downvote, filter, etc specific content. Let me trust (or negative-trust) other users (think of it like "friend" or "block", in simple terms)

Then, and this is the key... let me apply filters based on the sub/up/down/filter/etc actions of the people I trust, and the people they trust, etc, with diminishing returns as it gets farther away and based on how much people trust each other.

Finally, when I see problematic content, let me see the chain of trust that exposed me to it. If I trust you and you trust a Nazi, I may or may not spend time trying to convince you to un-trust that person, but if you fail or refuse then I can un-trust you to get Nazi(s) out of my feed.

It's a novel idea, I can certainly see the nice implications of it, but it also seems incredibly excessive. Would you really going around flagging every user you see on a trust system? Or even enough users for the system to be moderately effective? And then expect many other users to do the same?

I honestly don't think I'd use it, blocking people is enough for me.
- I maintained a substantial set of tags for problematic users of all types so I knew to avoid commenting or engaging with them. In an given community it's common for there to be a tiny percentage of prolific posters who are a real problem and tags with res is how I managed that. It absolutely can work and arguably twitter's block and mute functions do a similar thing as thevpy reduce a user's presentation considerably.
I think a thing like this will even be required in the near future. Because we can no longer trust that we are talking to real humans, therefore some trust system (including physical interaction perhaps?) will be needed to not get social networks drown in AI dystopia. I have bookmarked this comment which describes the krass scenario we might find ourselves in soon: https://lemmy.ml/comment/878882
@[email protected]
- Re "physical interaction"... Are you old and/or geeky enough to know about https://en.wikipedia.org/wiki/Key_signing_party ?
I found very interesting the concept of chain of trust :) What is the friend/foe/fan/freak?
- Slashdot has a friend list and foe list. Fan and freak are the lists of people who name you as friend and foe respectively.
  
  https://slashdot.org/faq/friends.shtml

Posts should just be upvoted and downvoted with no credit given to the person who posted. Same goes for comments. In my opinion, upvoting and downvoting should just help the user find the most relevant information. Content that people upvote is the most seen. Content that people downvote is the least seen. Posters and commenters stay on an equal footing with no points system.

Maybe we could still have karma, but display it as a ratio of good:bad karma or something? Active user and most of your interactions get upvoted, green dot. New user or not active for a while? Gray dot. Established user and all your content gets downvoted all the time, red dot.

Get banned from 50+ subreddits? Your color dot gets changed to a picture of u/spez.
- best idea I have heard thus far

Not really sure what you think is wrong with karma? most of reddit's problem IMO come down to bad moderation.

But for comment scoring, there are really just 3 methods I've seen:

Generic Up/Downvote - Reddit
Categorized Up/Downvote - Slashdot - This worked on a technical forum to keep technical knowledge near the top, while still allowing stupid/funny comments further down the page, plus it made ignoring stupid/funny threads easy
Personalized Up/Downvote - Facebook/Twitter/etc - basically build a profile of users you agree/interact with, and then weight their interactions accordingly to predict what content you'll like/hate.
- I believe Ticktok take this to the next level, because 90% of users don't up/downvote, ticktok logs the passive act of continuing to watch content as a partial upvote making their algorithms train on the average users likes/dislikes faster.

You could probably combine Personalized & Categorized, but I've AFAIK not seen it done.

I think the problems with moderation are harder to solve, because you have both bad-faith moderators & good-faith but easily played moderators as problems, and you also want different dynamics as forums grow.

I think lemmy could really experiment with good moderation & meta-moderation and if the developers are interested anyway, be a far better forum as a result.

Peer review of moderator decisions is something Slashdot did that went quite well. Once you'd been an active user with good "karma" for a while you would occasionally be asked to review other users votes, I think a similar thing could be done for moderation decisions
Elected mods. For subs above a certain size, having moderation essentially boil down to whatever the guy who created the sub decides, is bad. I don't know exactly how it would work to prevent abuse, but as subs grow, at some point it would be good if the community chose the mods.
- even short of full fledged democracy community approval of mod appointments would certainly reduce the amount of mod drama where it 1 bad head mod, will purge the other mods and replace them all with sock puppets.
Users-led replacement of bad mods, similar to electing mods, it would be good for users to "recall" a bad mod.
Transparency over mod actions, I understand that with the number of Nazis & other assorted trolls online reddit chose to let mods, moderate anonymously, but it really means you have no idea who is doing a good/bad job in many subreddits, some level of transparency for all but the worst content is key.
Moving subs, as lemmy instances have some control over the content of the subs that reside on them, it would make sense for there to be some method for the users + mods of a sub to decide to move it to another instances. This not only prevents admin abuse, but also encourages competition between instances for technical administration & content administration.
Splitting communities , sometimes subs grow "too big" and have different subcommunities that end up fighting for control of a sub, it would be good if there were a way of these communities splitting into 2 rather than fighting over the original name. not sure how it would work, but thinking about how r/trees & r/cannabis split or something similar. Maybe /r/canabis could become an combo of /r/canabisnews & /r/canabismemes, where users can just ubsub from the 1/2 of the content they don't want.
Letting users weight subs/filter subs how much of subs they see, sometimes I've unsubbed from a high-content sub, just because while i liked the content it was overpowering the rest of my feed, it would be nice to have users configure how much of a sub they see (especially if combined with Categorized Up/Downvote), rather than complaining about "bad moderation" I can just personally choose to see less of what I don't want.

Anyway thank you for reading/not-reading my ted talk, but I suspect this will come up again so now I can copy/pasta it.

Periodic mod elections would be fucking dope tbh.
Slashdot did so many things right. +5 Insightful.

One feature I liked a lot from RES was the ability to tag users, which I used to flag users and remember who they are and what their general opinions are on issues. It made arguing more interesting since I didn't have to rerun over the same old conflicts with people who will never budge on certain issues.

Or on the more positive side flair people who are really helpful . And flag them once then start to see that whenever they post something helpful it's the same person. Funny thing is I would still never remember the username. Flair would just be like helpful person who said how to fix settings.

Embrace the Lemmy system. Resistance is futile. Fake internet points are futile.

Subs should be able to force sort by controversial for comments and/or posts.

Any damn fool can come up with comments that are universally approved of, or universally hated. They aren't interesting.

The phrase 'trivially true' applies - "This crime was a bad thing, and the people responsible shouldn't have done it! I am very angry at them!" may be emotionally satisfying to say or to cheer on, but it doesn't add a damn thing to the conversation, any more than "hur hur suck it libruls" does.

There isn't a term for the inverse of ragebait, but there needs to be. All the le reddit moments - the tedious meme-chains, forced in-jokes, etc.

For subs where you want interesting discussion, you want to sort both to the bottom. It's the posts that divide opinions that are worth talking about, almost by definition. If a post has a thousand votes but the total is close to zero, well hey, that's probably worth seeing and engaging wth.

Let people vote with their heart, use upvotes/downvotes however the fuck they want to instead of constantly nagging and whining about it - and then use that to detect and de-prioritise mediocrity.

It wouldn't be appropriate for all subs, but for some places, I think it'd be a huge improvement.

Top 3 most upvoted comments always being unfunny puns was getting insufferable on Reddit. Everyone was trying to be a fucking comedian - that's what was popular and got upvotes.

The early Reddit you could have long, interesting arguments with people and you'd both be getting upvoted because you're both making interesting points.

It honestly feels like my brain is waking up from a digital coma since coming to Lemmy from Reddit. My own personality and opinions don't feel pointlessly supressed and sanitised.
I really like this solution. Instead of making things more complicated for users or trying to control their input, observe their natural behavior and then respond to it.
Judging by the controversial comments on Reddit, I don't know if I want to engage with 50/50 up/downvotes for any significant amount of time. I think a 60/40 ratio might be a bit more palatable while still keeping it engaging. I'm not convinced an algorithm like this is the best course of action though.
"tell the truth" always brings the best reaction
We aren't here to get popcorn out over the kind of clown Fiesta found in reddit comments. Comments are for constructive discussion not entertainment.

Ok jerboa is lying to me this morning.
Making a controversial statement for attention is just as easy. What you are proposing would be a perfect environment for trolls.
- Not a statement that makes people angry, because that would get ignored or downvoted. One that garners both positive and negative reactions in equal measure. That's a lot harder to engineer; you need to look at both sides and walk the line between, pretty much getting to the crux of the issue. If the crowd can't decide whether they agree or disagree, then to me that means it bears looking at more closely.

What about hidden karma?
Like there is still karma used internally to decide what posts to promote and how to weight votes, but the numbers are kept only internally so people don't get obsessed with that number next to their (and others') profile?

Or what if a user could see their own karma, but no one else's? If karma isn't publicly visible, then people may care less about it.
I think this would make people more obsessed. We would see the rise of SEO-like shenanigans where they would try to guess what makes the internal algorithm tick, complete with “karma experts” to advise you on how to optimize, etc. more of a shitshow that just having it plainly visible, I think…
- Well, I was assuming we were talking about open-source software. So you wouldn't need karma experts to "guess what makes the internal algorithm tick". If it's open source, the algorithm is still public. You just wouldn't know how much karma each user has.
No, no, no, please no hidden algorithm. that's as bad or worse than karma, especially with the incoming bot shitstorm.
- I didn't say hidden algorithm. I was assuming we were talking about open-source software and hence public algorithm.
  It's just your karma points that would just be kept in the database without putting that number in your profile.
  That changes nothing in terms of how the algorithm works. I didn't suggest changing anything on how many details are available on how the algorithm works.
Tbh this is what turned me off the thunder app.
given how instances have been popping up with massive amounts of bots recently and someone even managed to get on top posts from bot upvotes recently, right now this probably wouldn't be a good idea... Though I tried looking back for the post I'm referring to and can't find it. maybe it got dealt with, title was like "Protect. Moderate. Purge your server" or something? the guy botted upvotes to promote to instance owners how to protect themselves from bots

Why not keep the scores hidden and just use them to order stuff?

For individual posts/comments that's doable, I think the main issue is "account karma"

I like the system as it is here at the moment. Up-/Downvotes per Post/Comment to show the popularity (and express (dis-)approval). But nothing to collect per account, so noone gets encouraged to post just for the karma.

I don't mind the karma system for users - it let me know at quick glance who to block. All of those mega users posted the most basic of content that just flooded my home page.

I could still do that by just browsing their post history, but it made it easier at a glance.
- Yes, but having a trackable number is what incentivises many people to farm it
  
  No reason to add a feature if it makes the problem worse

my take: up only, no down, per-post only, no account karma. if someone is repeatedly a problem mods can show them the door.

karma systems have been around forever allegedly to decrease mod/admin workload managing users by having them "self moderate" and that has NEVER been the actual effect - they've only ever been an engagement metric for advertising and it didn't matter positive or negative if people were angry downvoting they were still engaged. I've witnessed site after site add these systems and then the userbase turn into a toxic cesspool after. In almost 30 years I've only seen one roll back the change even partially. Their culture never fully recovered and its still dominated by people agitating to get attention and to one-up their perceived rivals.

Let reddit things die with reddit. Long live Lemmy.

I very much disagree with the "no downvote" opinion. It leads to homophobic, racist and generally bigoted comments getting much more displayed appreciation than they should (see: any YouTube comments interaction).

You can say it's the job of the moderation to take care of that kind of hateful content, but I prefer that content to be displayed as a rejected and challenged onpinion rather than not addressed or ignored. And for that, a quick downvote + sourced debate is better than an unending thread of wordsoup where even the most hateful argument only gets shown some love in the form of upvotes.
- You can say it’s the job of the moderation to take care of that kind of hateful content,
  
  I can and I do :) ..also its usually what will happen anyway, downvotes or not.
  
  It leads to homophobic, racist and generally bigoted comments getting much more displayed appreciation than they should (see: any YouTube comments interaction).
  
  youtube comments are a very special kind of cesspool. The things you describe should be removed by moderator, downvotes aren't enough to detur that. Those types of comments should be reported, the post removed, and the user kicked to the curb for saying them. No tolerance for that. No debate is going to change anyone's mind, its just giving them room to argue in bad faith to further spew their hate.
  
  Anything not worth a ban, is very perfectly debatable without a negative number telling me who's opinion the unpopular one (or had more/less puppets to influence it, as sometimes is the case).
Beehaw runs without downvotes, and so far it's encouraging. I had a civil discussion with someone in what on Reddit would have been a downvote-fuelled flame war.
- I have felt the same way on several lemmy instances now - that whole culture just isn't here so far. People speak what they are thinking and aren't randomly crapped on for it. if someone disagrees, they just say so and why. Its wonderful.
I'd also add a (funny/informative/opinion) vote button aswell. These spaces can become noise drowners where information can be drowned by repeated jokes that get upvoted to the top. Too many times I've seen conversations like "Does this mean I can do A or B? - Yes."
Itgets really exhausting. Having an easy filter to skip the noise would be great.
- 2nd time on this topic I've said it but then we're just recreating slashdot's old system.

Karma and votes should stay but be hidden to other users. Karma is a good way to detect bots and trolls, but just admins and moderators should see it to act on them if needed. And up/down votes should be hidden too because of the hive mind phenomenon that it produces (Experienced on Reddit): often, the funny or sassy or apparently clever comment gets upvoted and sometimes, the comment with knowledge about the post gets downvoted because the first joke was funny. Many people may not have an opinion about the issue but upvote the funny guy and downvotes the real answer just following the hive. Hiding it, each person reading must decide by themselves if they upvote or downvote a comment.

Prizes and awards could maybe stay, not sure

Prizes and awards could maybe stay, not sure

They should be used to fund the servers.

In combination with invisible vote scores and no karma it would be a good way to highlight great content without feeding into dopamine addiction.
often, the funny or sassy or apparently clever comment gets upvoted and sometimes, the comment with knowledge about the post gets downvoted because the first joke was funny

This is why I like the option of having different vote categories with corresponding sort options. Sometimes I'm specifically looking for information, sometimes I'm just killing some time and don't mind the fun.
the funny or sassy or apparently clever comment gets upvoted and sometimes, the comment with knowledge about the post gets downvoted because the first joke was funny. Many people may not have an opinion about the issue but upvote the funny guy and downvotes the real answer

That had me refusing to participate on posts entirely. It made Reddit less of a place for rational discussion and more of a frustrating popularity club.

Am I the only one who purged reddit accounts when it became too personal?

I did the same thing but it started to become impractical when quite literally all subs I regularly used added a minimum karma requirement. Even getting some low amount like 5 karma is hard if you can't post anywhere you care about.
I did the same. I made a new throwaway every few months or so.
I did that too. Was annoying not being able to post in half the communities I enjoyed everytime I did this.

But much less annoying than getting doxxed.
Does Lemmy provide enough content to substitute Reddit?

I like it as it is to be honest.

Personally i like to call em WIP. Worthless internet points. Just to be clear i cherish my WIP. I would never disrespect my WIP. That's just my name for it.

How about expanding the votes into multiple kinds of karma. Make it possible to place several votes: "on topic/off topic", "funny/boring", "shit post", "solution to the question", "agree/disagree", "political", "Interesting", "Spam", "Original Content", etc.

Communities could create whatever rating is suitable for their forum.

Sort of like tags, but votable.

It would basically reward everyone for what they do (being a level 7 funny shitposter is something) but at the same time making it possible for others to filter out anything they don't care about. So instead of clicking downvote because of disagreement or upvote because it's funny, there would be an outlet for that in its own vote.

I feel that would make it easier to find quality content whether you're looking for serious debate or the hottest memes.

We'd need better comment filtering on individual communities, and it could/would be abused, but overall it would be facilitate the possibility of having different kinds of conversations on the same topic.

Sometimes I want to read funny stuff in serious topics and sometimes there is serious stuff in funny threads, and sometimes people write clever stuff that I disagree with and so on. One vote is just not enough.

Yes, I like that, there should be like 3 dots with a up/downvote logo on top of it and when you click it you would have the options to like: -downvote: off topic -Upvote: Intersesting -Upvote: Original content

And so on
So go full circle and recreate slashdot? 5:Insightful

I have mixed feelings on this leaning towards "please no, not this"

No rating system can substitute for good moderators that pay attention and users that report when needed. everything else devolves into toxic behaviors.
- What is Lsashdot?
Sounds like FB reactions but much more useful

(1) No Karma system at all

(2) Karma spread over several numbers rather that one; think of Github's user page for example, stats for everything in general on one's profile to reflect general activity

(3) Community award badges

I do like the community badges. And honestly, I would be ok if "karma" was how many "gold" awards a user received, at least there would be some monetary rate limit there to prevent bots from gaming the karma system. Also Lemmy communities would benefit and it would help pay for server costs.
- I agree that it would have to have lots of rules and limits to discourage bots/farming.
  
  Having it help fund the servers is an excellent idea, fully community-driven.
Community awards would be great. It encourages quality content and can strike a balance between new and old users.

I don't think having a rating system that could be farmed or abused is a good solution. There should be no incentive to generate content just for the publicity of the account. All the content ends up being reposts of low-effort things that are just more relatable, which, in all honesty, I find really lame.

What other methods would there be to find bad actors? Do you think karma does a good work on finding bad actors?
- Karma is like a high score that everyone is trying to achieve. It is more of an engagement metric rather than a quality or moderation one.
  
  You can use monitoring tools on the backend to count the number of removed posts and moderation actions taken on an account that is only accessible to moderators. This information does not need to be public, but it could, like how Steam displays VAC bans.
  
  Currently, everyone's post and comment history is public on their profile I think.

I loved forums, and we didn't have anything, except for 'total posts' and 'total replies' for users. I like that.

I do like upvoting, but I think karma should be hidden. Maybe if you go to user profile and click a button to see the value. It should not show if you hover over the user in a discussion, like Reddit. This is too much incentive for Karma farming.

I don't like downvotes, and that's the reason I'm on lemmy.one - no downvotes here at all

I would have optional, per magazine karma. Mods can decide if they want to enable it and what rules it should follow. Personally, i would max it at some low number, like 100; above that you are an upstanding member of society and that's it.

Initially I was bummed out about not having internet points here like on reddit. However after considering the fluidity this offers... like being whoever you want to be anywhere you want... being able to migrate from one server to another... etc ithink I'd rather we keep it this way to avoid complications

Advogato reputations: https://en.wikipedia.org/wiki/Advogato#Trust_metric

Added: also, Slashdot.org karma worked sort of like reddit karma except 1) you couldn't see anyone's karma except your own, and 2) it only had 5 or so levels, topping out at "excellent". It took a few dozen good posts to reach excellent, and there was no point to whoring after you reached that level. Posts were ranked by upvotes/downvotes and went from -2 to +5. Anonymous posts started out at 0, posts from registered users with non-negative karma started at 1, and posts from registered users with good or higher karma started at 2. There were some more complications including voting "insightful", "funny", etc. and there was "meta moderation" where you could judge the accuracy of other people's votes. Usefully, you could select "filter out all posts rated below N" where you could choose N. Looking at just the 5-rated posts gave you a quick overview of the worthwhile thoughts on that topic. There were often 1000+ comments in a thread, so no way to read them all, but reading the few dozen top ones was generally enlightening.

Oh yes I remember, you could only vote on posts if you were a moderator (in their sense of the term) at that moment. Moderators were picked at random on a daily basis from the population of users with positive karma, or something similar. You got five "mod points" which you could spend on voting on posts, i.e. you could only rate 5 posts during your day as a mod, rather than all the posts you saw. You tended to get mod points once a month or so. It has been a long time since I spent any time there, so my memory is a bit hazy. It went down the tubes for a while, though recently it has looked better.

I really like this karma method, but I'm curious about what led the site to going down the tubes for a bit there. Was that in any way a byproduct of the karma system, or other issues entirely?
- Major UI changes. It was so hates that a small group forked the code and started Soylent news.org
  
  To be fair, the UI changes were rather bad.
- There were a bunch of reasons people left. Personally, I thought the slashdot site redesign really sucked. They ruined the comment section. It was harder to follow comments and it seemed the amount of comments shown varied at random. Sometimes you would only see high rated comments, other times it showed all, even the troll comments. It was weird. And the look of the design was weird. Oversized margins that forced more scrolling. There were a few other things I didn't like, but those were negligible.
  
  There was also the sourceforge drama where slashdot buried negative articles about sourceforge, its sister company. Hard to trust a site much after.
  
  Overall, its still usable. I still stop in once in a while to read tech news, but that's it. Those stop ins are getting less and less, too. HN is my main go to for tech stuff.
- Why did Slashdot go down the tubes? Nothing to do with moderation, just management screwups similar to the ones Reddit has had a few times. Slashdot was sort of a 1990's version of Reddit. It was sold a few different times and the new owners tended to try to impose unpopular changes. Those did usually get rolled back.
  
  Re the moderation system itself, I suspect it went through a lot of iterations. Slashdot was die-hard about free speech so had tons of trolls and spammers, but made the karma system work well enough that you could keep away from the trolling unless you chose to browse at -1. I think -2 was added sometime later when -1 was seen as not low enough. Generally you could do ok by browsing at +3. They asked for mods to browse at -1 so that you could upvote stuff that was downvoted wrongly.
  
  More info: https://en.wikipedia.org/wiki/Slashdot#Peer_moderation
  
  It says they killed off anonymous posting in 2019, oh well. I had always thought that was a good feature despite the crap that got posted that way.

What if we had a community standing metric that flips only between "good" and "bad."

You get "bad standing" if the majority of your contributions in the last 6 months have a majority of downvotes than upvotes, but it resets after 6 months.

Everyone defaults to "good standing".

This serves the purpose of a metric to filter out trolls or bad-faith actors, whilst making "karma farming" pointless.

People commonly use the downvote button as a way to indicate that they disagree. I'm not in favor of punishing unpopular opinions when they're expressed in good faith.

But I also can't think of a system where "troll or bad content" can be separated from "I don't like what I read".

The more we push popular opinions the more of them will be shared, leading to communities becoming echo chambers and even good faith arguments against the common consensus will be lumped together with the worst of bad actors.

This is exactly what I dislike about Reddit.
- But I also can’t think of a system where “troll or bad content” can be separated from “I don’t like what I read”.
  
  Me neither. People would just push whatever button means "punish commenter". Slashdot tried for a while with multiple scores given per comment like "funny", "informative", etc. It didn't take off.
- This is just human behaviour though friend, I don't think we can ever change that. People don't want to see what they don't want to see.. it's not necessarily a bad thing, and if you remove that power then you remove a lot of the motivation behind the platform.
I like the idea. Although I'd suggest a sliding window instead of a periodic reset.

I had a twinge of regret the first time I realized that my Lemmy account didn't have a cumulative tally. Then I realized I didn't actually want. I am better off without the gamification of everything - especially social interaction. It doesn't really serve a purpose outside of gatekeeping, and if we put it in for the purpose of gatekeeping I think we'd all agree (at least those of us who where bot-modded back in reddit) that it's a poor substitute for human intervention in keeping bots and bad actors out.

I agree mate. I joined Lemmy today, and I really appreciate the fact that there is no karma here. Until today, I’ve never believed that it was possible to have a non-gamified social network. We are here because we want to and we enjoy

Call it "updoots" instead.

MeowMeowBeenz would work wonders.

My meowmeow beenz :(
- I just gave you five meowmeow beenz to make you feel better!
What is that?

Score the posts, not the individuals. Attaching imaginary points to any kind of activity instantly turns it into a competition.

Instead, any scoring should focus on actual content, which is basically what the up/down vote is.

I like this, and I also remember forums where you knew that that type was good but weird, that one was nice but not very good etc etc. You had to build your "real" reputation because it was an enouy small space.

I hope Reddit will explode and create gazillions of normal sized subs...

People like big numbers. Karma systems exist because they encourage posting and engagement. Stifling growth because Karma is toxic is bad for everyone in the long run. What matters is growth.

I think it is fine now. I don't really want karma totals or a wave of different colored reactions. Upvotes or downvote. I can't even do downvote and haven't missed it.

How about just ignoring the whole concept? I.e., voting in individual threads to rank comments, and that's it.

In my opinion the best alternative is a -1 : +1 scale. Members who contribute little are near 0, members who contribute a lot in a positive way get towards +1, if users contribute a lot in a negative way, their score goes to -1.

There are lots of different particular ways to implement this that isn't up vs. downvote count. Communities created, moderation activity, post count, engagement per post, positive reporting rate, false reporting rate, number of reports against the user, number of communites banned from, etc.

yah, karma was garbage, I think we are better off without it.

Would you implement any other system?
- Nope, its fine the way it is.

Karma should have a half-life, so it's not a forever thing. Have each karma point lose half of its value every three days. Makes it more transitory.

But what if the thread is old and someone came across it from google looking for information?
- The thread doesn't get deleted - the user just loses the karma. So you post something helpful, it gets a ton of upvotes, and those votes expire over time. I come along, find your post via Google, and upvote you, that is a fresh upvote and counts, until it ultimately expires in six months, weeks, whatever, or gets a halflife as @[email protected] said.

I don't think there needs to be another system, just a lower emphasis on said system. Like others have said, just post karma.

Someone pointed out that if you make your own instance, you can probably just manipulate your reputation anyway, so it won't be in any way a judge of a person. Even then it was really only useful in extremes, aka if the person had a massively negative rep they were probably a troll, and a near-0 was a new account. Anything other than that was more a metric of time than anything else.

Sure, even post karma is an abusable system, but if you have nothing then you'll be wading through people ignoring others or using circular reasoning to make bad faith arguments. The system is good for at least dealing with extremes.

Here's a crazy idea. What if down voting a comment/post resulted in a weighted random float between 0-1 while upvoting resulted in a weighted random float between 1-2? If you virulently hate a comment or post, ignoring it is the surest way to bury in completely. Posts and comments that Garner attention become the most visible, but gaming the system for visibility could become difficult if the weighting algorithm was tuned appropriately.

It would also make botting comments to the top slightly more efficient

The problem isn't the points, it's the people. Everything starts to suck beyond some critical mass.

I agree that it might get toxic at one point, but I'd much rather see extra preventive measures to stop repost bots, karma farming and so on rather than removing points altogether. Maybe it also helps to see karma breakdown by community: say you see someone answering a technical question on a specialised community - it would be of little to no relevance there that they might have 10000 points on r/funny or r/aww - I'd much rather see their points on that specific community.

The worst part about using reddit when I first signed up was having to deal with celebrity redditors with bajillions of karma sucking all the air out of any thread they visited. Thankfully, it seems like over time people calmed down a bit with that, or maybe I just started browing non-defaults with more tight-knit communities, but you still have dumb novelty accounts that kind of ruin the experience (if you've ever been got by /u/shittymorph, you know what I'm talking about).

Yeah, but without the karma system these memes would never have existed. That's not to say the karma system is good. Quite the opposite actually.

Live and let live - Best system ever 👌

I for one wish we could return to the lawlessness of old phpBB boards from the late 90s. Weren't no karma points to work any back then.

Those boards were rife with toxicity. You’d have secret rooms with people attacking a commenter behind their back. Created a very ‘with us or against us’ vibe. Then it would hit a boiling point and spill out as a public attack on a commenter. It made the bullying premeditated and targeted.

I'd just like.. users have a comment count

and a post count

simply.

some people like to make posts

some like to just comment (this is mostly me)

i can also live without it but.. if there absolutely have to be something..

i dont like "karma" on reddit

Any shortcut method of mimicking reputation can be and thus will be abused, so they're all toxic.

The only sure way to do it is the good old-fashioned way - by name recognition - actual, earned "reputation."

The way it used to work on all forums and still does on some smaller ones is that people just read posts and write their own posts and over time they come to recognize each other's names and associate them with some impression of each individual's value as a poster.

And yes - that's not very effective in gigantic forums, and it's not accessible to newcomers. You need a relatively small group of posters and new people have to pay attention in order to figure out who are the better or worse posters. That's just the way it is, and is one of the problems with gigantic forums.

I'm not a fan of this because the main thing I liked about Reddit over all the other various "social media" was that I didn't have to try to recognize names. Names didn't matter, it was all about the conversation and the subject matter. If a post or comment was good I liked it, if it was bad I disliked it, and I moved on.

RES kept track of my personal like/dislike sum for each individual, perhaps since upvotes/downvotes aren't anonymous here in the Fediverse it'd be more straightforward to do that and show that to each user.
- @[email protected] I actively jam this by changing my name every so often like a molting arthropod
by name recognition - actual, earned "reputation."

That...is going to mean most people are untrustworthy after a few months. You won't recognize most people you speak to.

Keep in mind forums also usually only had maybe a 100 people at the most. We're dealing with potentially thousands in one thread.

I also find it really strange you gave that as "The Only Way", then by the end said that it doesn't really apply here.
Yes, this.

It's not like karma worked well as a reputation system, anyway. In a large forum, all it points to is that you were lucky or entertaining. It says nothing a out whether you're actually a positive influence on a space.

Post the same post as 36 other people, but because if random chance yours gets chosen to float to the top? Co gratulations, you have a severe positive karma score for life for doing nothing different from those who got nothing.

Dunk on people in a way that others think is entertaining or deserved? Bam, you're swimming in positive reputation for being an asshole.

It doesn't create healthy space. It doesn't denote that you're a net benefit to a communal space. It's not even proportionate to how well you're known.

It's just gamed fake internet points.
This could work in a small community. When there is a community of 2M active users, remembering more than 10 names becomes extremely hard ;(

I think if we feel the need to do anything like it, chasing the number alone will be what makes people insufferable. Maybe track it invisibly on the instance where the account is hosted and display only a colour. Red for negative points, yellow up to maybe 50ish, and anything above is green. Enough to pick out the trolls while providing no reward for karma chasers. I don't think anything beyond that is useful.

Personally, I enjoy how 4chan does it. Posts are anonymous and seen in chronological order. There are no upvotes/downvotes and no karma or e-peen linked to accounts. Also, everything is temporary and gets deleted off the site completely eventually.

The pros are that you have to judge posts based on its content and nothing else, and can't look through someone's post history and stalk them across the site.

The cons are that you have to shift through tonnes of shitposts just to find decent content which will eventually get deleted. You can't find the top posts of all time, because they're gone. The system also makes it a great place for trolls. 4chan has so many of them that threads entirely made up of trolls trolling trolls is a thing.

If you're looking for a site that ranks the best content then a voting system is needed. If you're looking for discussion then a voting system and permanent accounts only get in the way.

Non-algorithmic ordering, auto-collapse replies after a certain user-preferred setting.

No up/down votes obviously.

Personally I think there shouldn't be anything like it at all , that stuff should only be visible to you and nobody else . Didn't stop reddit from becoming toxic cesspit . But once its implemented it's hard to remove w/o serious consequnces . Just look at youtube dislikes .

Worst thing about karma system, r/assistance has minimum karma requirement which I think is shitty to peops who need help

Downvotes only so karma whores never comment, and completely random monthly account bannings so no one gets too comfortable.

The Russian roulette strategy for content aggregation.
I loved the random monthly account banning 😂 I’d do it pemaban and hold a big event to decide the lucky winners~

This may be a dumb Idee so please go ahead and tell me if it is. It seem ppl use it to know who to block in advance. What if you get a red name or some kind of info on the profile if the account has been blocked by other users and it is above 10 or 20 blocks? Would that help? That would suck for that account because it will forever be the ass hole account. But at least no one would really want to farm that except the trolls who want ppl to know they are trolls.

I like how it is now tho. It is good when the mods are responsible first and foremost instead of a system.

I like that way of thinking, however, people could exploit that. Imagine you are in a chat about colour blue, then you say colour red is better. You get downvoted for having an opinion different from others. That would make people follow the hive-mind so their colour doesn’t turn red
- wait, are you saying ppl would block the person with a different opinion so their account 's name turns red (essentially bulling) so it will make other ppl block that person too even tho the person said something like "red is my favorite color!"?... ppl are scary. I guess we shouldn't have a system then because we can't have nice things :(

I still firmly believe one of the worst things to happen to the internet, besides pop-up ads, is up and down votes. Nothing exposes a misanthrope quicker than forcing them to comment instead of passively downvoting everything they see. Which makes it easier to remove them from the party.

In a way down votes are necessary evil. One of the quickest ways to suppress off topic, trolls, spam etc.
I think you've got the wrong idea about misanthropes. But who cares? You're only interested in excluding people who disagree with you and reinforcing an echo chamber for yourself.

You're just as much a source of toxicity in these forums as those you wish you could ban from them.

If there has to be something then probably karma that is strictly for the past month of activities. It's not permanent so there's no point in people accumulating it to sell or trying to karma whore. This way it also has an indication that could still help people identify trolls at a glance.

Personally, I don't think there needs to be any indication beyond how hidden the content is. Karma's goal is to push "good" content up and "bad" content down. Users don't need to see what's essentially a like/dislike counter for that to work, and I don't think it's conducive to civilized discussion. The fediverse makes votes publicly available information, but that doesn't stop kneejerk anger-downvoting, it just means people can retaliate easier, which feels good to do, but isn't healthy.
Related to this, one thing I've seen on Youtube & elsewhere is troll-alerting on ancient vids & posts, causing users to get slapped right & left for ridiculous bullshit.

I propose a general statute of limitations - no banning or punishments for crap that was posted more than a month ago.

I couldn't care less about karma, what I really want is a way to see what I upvote, otherwise I feel that what I upvote is meaningless (for myself, I like to boost content that I like though).

As a moderator, looking at karma is one of the ways we can automate the blocking of potentially unwanted content.

As an also recently-former user, I don't feel like Reddit gets to own the upvote/downvote function, and I still like it more than some like FB/Twitter/YT Thumbs Up. I think it would be cool for some independent communities to remove the function for more team-oriented conversations, but on the larger forums like .world is turning out to be it should remain as is.

We need the karma-equivalent of PageRank. Every vote should not be treated the same, just as Google doesn't weight every link equally. The "one user one vote" system is the equivalent of pre-Google search engines that would rank pages by how many times they contained the search term. But it can't be as simple as "votes from higher-karma users are worth more" because the easiest way to build insane karma is to build a bot or spam low-effort replies to every rising post. Still, the system needs to be able to extract the wisdom of the crowd from the stupidity of the crowd, and the only way to do that is to apply a weighting gradient to users and their votes.

How would you separate the wisdom of the crowd from its stupidity?
- If there was an easy answer, someone would have implemented it already. Obviously, it's a challenging problem, and I don't claim to have the solution.
  
  I think expanding the voting dimensions (a la Slashdot) would make it easier to create an algorithm, but it pushes complexity to the user, so that's a tradeoff.
  
  But, even with up/down votes, I think there are potential ways of identifying users whose votes deserve more weight. For instance, someone who up-votes both sides of an argument chain (because both sides are making good-faith responses and adding to the conversation) should be boosted.

I asked chatgpt, just to see what would filter out...

I would like some advice on designing a content-sorting and content-filtering mechanisms for discussion forums, in order to avoid or mitigates some of the problems that current systems are prone to.

One of the social problems with discussion forums results from the concept of upvoting or downvoting content.

It can be argued that voting content up or down serves to sort content by quality, allowing high-quality content to be seen and engaged with, while discouraging low-quality submissions.

However, in practice, Goodhart's law ends up applying: when a measure becomes a goal, it stops being a useful measure.

By using popularity as a proxy metric to determine quality, and by rewarding popularity with positive attention, this ends up selecting for content with superficial emotional appeal - ragebait, memes, facile/obvious comments pandering to common sentiment, puns, etc. - and not 'useful' content that is thoughtful, incisive, analytical, or important-yet-unpalatable. Ironically, content of this nature is also low-quality in a different way.

Worse, this ends up training users to produce content of this nature at the expense of thoughtful, interesting, incisive discussion, reducing both the production of quality content, and the quality of the collaborative sorting that users perfom by way of voting.

A cumulative 'karma' score for users, being a sum total of their upvotes and downvotes across all of their submissions, while ostensibly encouraging engagement and admirable behaviour... can again end up being gamified, and lead to users making large numbers of popular but low-effort submissions in order to maximise their score.

This can also produce 'filter bubbles' or 'hive minds': subcultures or communities that reject and discourage disagreement or criticism, and end up with a positive feedback loop leading to increasing orthodoxy with little grounding in reality. In some cases, the communities involved can become radicalised or toxic as a result, as more-moderate voices are suppressed from the discussion, and increasingly-extreme views become required in order to gain attention. Of course, it's reasonable and useful to let groups based around common ideals preserve an individual identity separate from the mainstream of discussion, but perhaps a way to regulate excessive self-selection would be useful.

Doing away with any kind of quality-sorting mechanic altogether is not a very useful alternative; a forum where spam, antisocial, or irrelevant submissions are given equal weight and visibility as interesting or thought-provoking posts tends to discourage users from participating or even reading.

As a further complication, users do not generally follow instructions or policy set out for voting on posts, and will tend to use them to indicate approval/agreement regardless.

Human moderation is an important part of any discussion forum and essential to the guidance ans shaping of any community, but the workload does not scale well; it should be considered a limited and intensive resource.

It would seem there are a few challenges to overcome:

1: Better-define the concept of 'quality' for discussion-forum posts beyond immediate, superficial emotional appeal - what is it that makes discussions feel satisfying, and drives deeper engagement? 2: Find a way to programatically ascribe a metric based on this concept, via the engagement of other users, in any form including upvotes, downvotes, tagging, commenting - and statistical or derived data such as the number, depth and overall score of replies to the post, and perhaps even analysis of the text of replies. 3: Ensure that any such system is difficult for individual users to exploit or game; for instance a naive reply-count metric could be trivially exploited by a user posting a large number of replies to a single comment.
4: Limit the effect of self-selection feedback loops, to prevent radicalisation while still allowing common ideals and identity to flourish in their own spaces.

One idea I've had would be to sort all content by 'controversialness' - that is to say, posts with a high number of total votes, but a low-magnitude score once downvotes are subtracted from upvotes. I believe this would tend to deprioritize low-effort posts such as ragebait or pandering to common sentiment, along with junk, spam and boring or irrelevant content, and thus bring 'interesting' content to the top. I believe it would be difficult to game for attention, or for other users to have undue effect on its visibility. However, I'm not sure whether controversialness would be a good metric to drive engagement, or what large-scale effects sorting on this metric might have on a community.

Can you offer any advice or commentary on the situation, or identify any important flaws in my analysis? Can you suggest any alternatives that might work better?

===================================================================================== ChatGPT You've outlined several important challenges and considerations when it comes to designing content-sorting and filtering mechanisms for discussion forums. The issues you've raised are indeed prevalent in many online communities, and finding effective solutions can be complex. I'll provide some advice and commentary on your analysis, as well as suggest alternative approaches that might address the problems you've highlighted.

Better defining quality: You're right in emphasizing the need to define quality beyond superficial emotional appeal. One way to approach this is by incorporating multiple dimensions of quality, such as insightful analysis, thought-provoking content, well-reasoned arguments, and valuable information. Encouraging constructive and meaningful discussions should be a primary goal.

Ascribing metrics based on user engagement: Rather than relying solely on upvotes and downvotes, consider implementing a more comprehensive metric that takes into account various aspects of user engagement. This could include factors such as the number of replies, the depth of discussion, the length of time spent reading the post, and even sentiment analysis of the comments. By incorporating a broader set of metrics, you can obtain a more nuanced understanding of user engagement and use it to evaluate content quality.

Avoiding gaming and exploitation: To mitigate the risk of individuals exploiting the system, it's crucial to design mechanisms that discourage or penalize excessive or low-quality contributions. For example, you could implement rate-limiting measures that prevent users from making an excessive number of submissions within a certain time frame. Additionally, considering the quality of the engagement (e.g., the relevance, thoughtfulness, and contribution to the discussion) rather than just the quantity (e.g., sheer number of replies) can help minimize gaming attempts.

Addressing self-selection feedback loops: To prevent echo chambers and radicalization, it's important to strike a balance between allowing communities with common ideals to flourish and promoting diverse perspectives. You could introduce mechanisms that encourage exposure to alternative viewpoints, such as algorithms that prioritize showing posts to users with different preferences or even implementing mandatory or randomized exposure to different topics or communities. Additionally, fostering a culture of respectful and open-minded discussion can help create an environment where diverse opinions are valued.

Regarding your idea of sorting content by controversialness, it could be an interesting approach to promoting engaging discussions. However, it's important to carefully consider the potential effects of such sorting on the community. Controversial topics and discussions can be divisive, and if not managed well, they may lead to increased conflict and hostility. Implementing safeguards, such as active moderation and community guidelines, would be essential in maintaining a healthy and constructive environment.

In conclusion, tackling the challenges of content sorting and filtering in discussion forums requires a multifaceted approach. By defining quality beyond superficial appeal, incorporating comprehensive engagement metrics, preventing gaming and exploitation, and addressing self-selection feedback loops, you can design a system that promotes meaningful discussions while minimizing the negative effects associated with current mechanisms. It's crucial to iterate and refine these systems based on user feedback and community dynamics to ensure the best possible experience for forum participants.

This is a great example of how aggressively useless chatgpt is at this kind of thing, the response is literally just the prompt rephrased and packaged like an answer lol
- heh, yep - it's just fancy autocomplete after all.
  
  I sometimes wonder if humans are really a lot more than that, though...
Thanks for the great comment. This multifaceted approach sounds intriguing, but may produce a black box effect, wherein users don't even understand the system or whether behaviors they engage in are contributory or detrimental to the community as a whole. How technically difficult would such a system be to implement and furthermore to properly convey meaning to users about their engagement with it? How could it be implemented to provide the psychologically rewarding effects, like karma does, to encourage further engagement without gamefying the system to the point of reaching the pitfalls you outlined of the current system?

I was thinking maybe some kind of ranking system like Street Fighter 6?

I know everyone seems to be hating karma but I do like that dopamine release. Ofx it will get abused... but what if there are just tiers, rather than seeing a number go up.

And at the highest tier, it doesn't matter anymore. That was you can see who is most active and it kind of gives just a bit of prestige. Furthermore, you won't see a number going up forever, so after awhile it's not like you want to keep gaming the system to see the number go up. But at the same time you can feel some some of progression.

Anyways, it's just a random thought I had as I am grinding on SF6 today haha. I could easily do without karma but it's just a thought.

What would you think about actual levels that the users could have and increase as they participate in conversations. That would not take into account the quality of the posts tho

Honestly it's pretty good to have the transparency of who is up voting, and down voting. Makes it easier to figure out who's farming or not. It's pretty good against the trolls too imo.

Other methods of what?

Shearing elephants for wool. What do you think?
- It sounds like hes asking, since nobody wants karma, what can we do instead that's just like karma, but I'm giving him the benefit of the doubt.

It's very easily abused. Does Karma affect article and comment visibility on Reddit? I don't know the details, but if so I'd suggest that it not do so here. Maybe just have it be a number calculated from boosts, upvotes and downvotes that you can see on the profile if you are a mod trying to determine if someone tends to troll, but not something that has any affect on whether or not your stuff is displayed.

Some moderators put thresholds on karma for an account to post, but the thresholds are always very low -- they are basically ways to work around open registration to get rid of throwaway account trolls and bots.

The downside is that this created an incentive to build bots capable of generating karma in order to become accounts that could spam/scam. The most common method was the repost bots, that would just copy and paste a comment from somewhere else in the thread or a post from months ago. That was annoying.

The actual "better system" is to just not have open registration and/or have active moderators that quickly get rid of trolls and bots. All the karma/reputation-based stuff is just heuristics to make that job a bit easier. No reason to rethink the wheel here.
Sort of.

On reddit, moderators can set minimum karma thresholds to control who can post in the sub, admins can use it to control who posts anywhere sitewide.

For example, new users who make a contentious statement and get down voted for it will suddenly find themselves rate limited for posting comments. They could be in the middle of an exchange where the other user is firing back responses, but then suddenly they are restricted to making one post every few minutes in the sub.

Admin can also use that to automate things like shadow banning.

I'm not from reddit, what is a reputation and what practical effect does it have? Is it just upvotes minus downvotes?

I found a reputation in my profile of "1" but I don't have a clue where that came from. I'm not sure why we need to have scores associated with our accounts, that in itself seems toxic to me to care about (clout chasing).

Upvoting comments in threads makes sense, I'm just not seeing any actual practical connection with the thing called "reputation" on my profile. What does it do in a best case?

Upvotes are a little broken right now, they work for sorting purposes but don't reflect on Rep. The "boost" option is equivalent to the reddit upvote or the Favorite option for Mastodon.

So Reputation at this point is just Boosts - Downvotes. It is likely that this system will be adjusted.
Yes, reddit's "karma" score was your (upvotes-downvotes)=karma, with limits on how much a single post couple affect your overall score. I've been told that Rep here on kbin is your (boost count-downvotes), with upvotes not changing your score. I'm also told that's a bug, but not what the equation is supposed to be.
On reddit, this was "karma," and it was your total upvotes minus downvotes, yeah. Socially, I know some people used it to judge whether the person they were fighting with had a strong history of acting like a troll (karma way in the negatives from all the previous downvotes).

Subreddits could also set minimum karma limits so anyone with less than X amount of karma (usually bot accounts) couldn't post there. Until the bot reposted something popular, and then they had all the karma they could want, so it wasn't really very useful imo.

On Kbin, it got renamed to "reputation," but it currently doesn't really do anything. Right now, there's also an issue with the way it's calculated: downvotes make your reputation go down, but upvotes do nothing. It's boosts that make the recipient's reputation go up/make the thing boosted more important to the algorithm.

The boost button is basically the retweet button, but since kbin is primarily used as a forum more than a blogging service, people are much more likely to downvote than they are to reblog anything and it can cause your reputation to be lower than it should be. The dev here has already acknowledged it as a problem.

Really, I wish the reputation counter on profiles would be removed in the future. It's only visible on kbin in the first place, and the main thing it accomplishes is encouraging people to ~~karma~~ reputation farm via low-effort reposts and comments so they can watch the funny number go up. There's no real reason to keep it.
- I appreciate that on Mastodon I had the ability to hide stats from my UI view, no harm making it optional I suppose.

I think the awards system from Reddit could work, just without it being monetized. The awards let you see how people feel about the comment, and it’s more than just good/bad, like/dislike.

Another user mentioned something like that! I like the idea :D
- I think it’s less braindead than the +/- system, which I think increases our engagement & makes us treat this place more like an irl_space

@VGarK Each of us individually, and the moderator group on each #Fediverse instance, de facto implements some form of trust [1] system, e.g. I block Alice and Dick but not Bob or Carol; and in Mastodon, I can add my private "note" about any user.

The question of finding trust (karma) systems [2] that the Fediverse considers ethically viable seems to be wide open to me: mathematically, psychologically and socially.

@nostupidquestions

[1] https://en.wikipedia.org/wiki/Trust_%28social_science%29

[2] https://en.wikipedia.org/wiki/Trust_metric

Hi Boud, thank you very much for the reply! I agree that each of us implements different connotations of trust, based on our experience. I understand that an ethical viable system seems to be wide open mathematically, psychologically and socially, however,I‘d love to know your view on a trust system that you’d agree on.

I think voting has the potential to be very useful but what we want to move away from is the reactionary "I disagree with you / dislike your post, so downvote"

One experiment I would like to see is requiring a reason when downvoting. Factually incorrect, violates this magazine's civility code, trolling, etc. Some reasons might have overlap with the report feature, so a downvote for e.g. illegal content might automatically notify the moderators as well. This might be contingent on a feature that can impose restrictions for abuse of the report feature.

Although it is already relatively easy for anyone to notice when an account is blanket downvoting a thread. In theory, it's already a bit easier for users to sniff out bad actors because they'll either have a clear pattern of misbehavior or a conspicuous lack of account age or participation

I like the idea of giving more information, however I’d say for both upvotes and downvotes. Me, as a user, I want to do things as quick as possible, so I’d say the action of upvoting/downvoting while giving more information should be embed into a quick wheel.

I like your comment, long press upvote and then select why in the categories. The same for downvoting

I think a reputation system is important, though reddit's current karma implementation is bad, there needs to be a method of identifying bad actors and forum shifters.

One refinement over karma could be that the score is kept only by community and should reflect that users contribution to the community.

Simple upvotes and downvotes also don't allow for nuance, replace them with a Buzzfeed like tag system (yes I know we all hate the site for its content but its tag system if used properly could be pretty powerful.

So instead of 'up' and 'down', you have a clickable emoji-menu like list of tags like 'interesting', 'boring', 'funny', 'WTF!?', 'Quality', 'Trash', 'Educational', 'CAT', etc...

So the reputation score for the community isn't just a flat number, rather it will tell you the kind of content a person posts over time, and doesn't carry just flat positive or negative connotation.

I mean the king of Catposting may have massive reputation in meme subs with high ranks in tags for 'Funny', 'Cute', and 'CAT' though that might not be the case if they participate in say a chemistry QnA community.

As these scores are created over time based on each users contributions (post AND comment reputation is the same thing) to the sub as scored by other people's tag selections for that users posts. The more it aligns with the community, the greater their contribution score.

Does this mean that toxic communities can form that exclude people based on reputation tags that the toxic community detests?

Unfortunately yes, that is one of the flaws of the system.

THOUGH

The fact it is contained by community means that a high rep person in an anti-trans community will not have any carryover reputation when joining a community they wish to brigade or degrade the quality of content, and their tag history will make it easy to determine their genuine engagement.

This was basically my idea, though as I've been reading through other people's posts and thinking about it a bit harder, I'd rather have something like an accolade system, which is basically what you described except the accolades or emojis available are decided either by op or by topic.

Personally I don't think negative options are terribly important, however I can see how in some cases they would be useful to have.

I would hope that there would be a quick limit of 2 or 3 accolades per topic, and having the topic sorted by whichever accolade people would be interested in. Such as a science post being sorted by either "informative" or "accurate" replies.

A more general topic like Pic sharing could have a few different accolades to give the post a quick tag to be sorted by. Things like "cute", "interesting", or "gross".

Users would gain a small color bar of accolades as they use the platform with an overall number of all of them and a brief breakdown of which accolades they have the most of.

To keep it tidy, we'd just need to create a short but useful list of accolades that would fit pretty much any type of content we can imagine, and I'd be interested in seeing a few "super accolades" for certain account types, such as bots.
So instead of 'up' and 'down', you have a clickable emoji-menu like list of tags like 'interesting', 'boring', 'funny', 'WTF!?', 'Quality', 'Trash', 'Educational', 'CAT', etc...

I'm not sure about this. How do you decide which qualities users can rate? How do you ensure those qualities work across instances with different languages / cultures? You're also taking something which is extremely low effort and making it take significantly more time and effort. I think the simplicity, universality, and low effort of upvote / downvote are all strengths.
- This would take some work, however, it is possible. Almost all the languages share some common concepts, such as love, hate, disgust, “what the eff”, cute… the symbology of them may be different, in japan, this🫰🏻means ❤️, for instance. It would be a matter of i18n the tags for a better localisation
- There will be a set of tags that the community settles on, things like 'funny' and 'informative', but also like with any hashtag I think users should be able to create their own and then let other users choose to use or ignore it. This means each community can create their own tag noetic library where the tags only apply to that community's meaning.
  
  For example the tag 'sick' may mean 'awesome' in the extreme sports subs but mean 'actually ill' in the medical subs, and people can use both freely knowing that it will be the community connotation that is used.
  
  This also means it is language agnostic and people can use the language they use the site in to create new tag clouds for communities.
  
  And with the coming AI chatbot age and forum manipulation, we NEED something better than simple, we need something adaptive, language agnostic, and community focused.
This is a new way of taking the whole + and -. I like it! Even if bad actors are “bottled” into specific communities is not something bad. You could identify those communities too. That would give the users more knowledge if they would want to join or not 👌🏻
Reddit's system is bad because the people who are meant to safeguard it don't.

Moderators of several big subs just don't care if people karma farm (e.g. bots who use their subs to build karma and a reputation to spam in other subs). Admin have gone on record saying subs like 'Freekarma4u' are fine because some subs have implemented minimum karma requirements. Tools which the admins gave mods to help control activity in their sub.

of course the biggest offender is users who can't be bothered to use the system with nuance. Did that person reply in a way that wasn't 100% cheerleading everything i Just said? downvote brigade!

The system works fine in theory, the problem is far too many people either ignore it or misuse it.

Tagging isn't very helpful. We've seen that in action on Steam reviews.
- I think the only way to really make this work is to have a crowdsourced safeguard system that doesn't rely on individuals.
  
  Personally I think tagging is the only thing that can work, because it is a multi axis upvote downvote system that simultaneously creates metadata that isn't tied to user identity.
  
  The reason it DOESN'T work on Steam reviews is that bad actors are not punished for 'joke' tags, and a persistent reputation system per user would fix that.
  
  When content gets a lot of views and engagement, the outlier engagement is easily identified, i.e. 'joke' tags, and a temporary decrement on that users's 'community power' can be enacted making each of the tags they use count for less than an average user.
  
  The opposite is true, people who frequently tag useful tags early can be identified, and given more community power, where their tags are worth temporarily slightly more than the average user.
  
  To keep 'community royalty' from forming, the extra community power for good tags decreases to normal over time, meaning that only through consistent and frequent community engagement can 'super users' maintain their power, meaing if they start to abuse it the backlash will decrement their community power back to a normal user quickly.
  
  With the explosion of forum manipulation and AI chatbots we NEED a better way, and the only way we are going to get there is trying new things.
  
  Well,. here's a new thing to try.

I think it would be better to have like a currency system where posts that are kept alive the longest trigger points, not just how many people upvote them. But then, you should be able to use those points to do something instead of hoarding them like a dragon's treasure or maybe turn them in to awards. If OTHER people give you awards, that's what you should have on display, not just how many upvotes you had. This would also give you more points for helping smaller communities create meaningful content instead of what's popular.

Something that is based on user activity and active users after a specific time. i.e the more users it has, the more highlighted it gets. (And before someone says about bots, etcetc that can be easily circumvented with filters and the like.)

From this and other posts on this as well as comments I read and discussions that made me think about it, here's my suggestion.

Upvotes and downvotes but lemmy allows people to only see upvotes in their client if they wish to (be it because they don't like the "negativity" of downvotes or because they're not very good at emotionally dealing with seeing their own comments downvoted)
Some kind of summary of upvotes/downvotes a user got on his or her posts, per forum and only if enabled in that forum. The objective being to as much as possive avoid the gamification side of karma and its side effects (i.e. people taking it in as a "score" which leads to things like karma farming) whilst preserving the positive side of it as a measure of domain expertise or at least willingness to positivelly participate in domain specific forums.

Thats just like 9gag, reddit, and the king youtube bs. If someone sees downvotes as negativity, it is already to late for him on a normal platform. A downvote should be something the author should see and know about. And other users should see that too. As it is a good content filter against clickbaity/scammer or just chatgpt answers.
- Whilst I personally agree with you that it's a good idea for an author to see both negative and positive feedback, I don't see what's the problem to allow the "criticism sensitive" types to protect themselves from criticism by toggling and option in their client which makes downvotes not visible to them (but it does nothing for others).
  
  For clarity, my suggestion is not to allow people to disable downvotes, it's to allow them to not see downvotes in their own client - downvotes are still there and everybody else who hasn't "disabled downvote display" on their clients can still see them.
  
  Think of it as a social interaction equivalent of installing ramps for people with disabilities on wheel chairs: nobody else is force to use the ramps but those who need them have them.

Every system that can be thought of (and has been suggested here) might sound great but when implemented at scale will no doubt prove to be open to abuse and require an army of mods to oversee. Otherwise every multi-million dollar social media company would have implemented it already.

Upvotes and downvotes and cumulative scores kind of do the job well enough that that’s what we keep ending up with.

That being said though, I would be interested in seeing a system where each downvote you make also counts against your own karma to discourage profligate use of the downvote to mean “I have a different opinion but can’t express it here”.

Edit: lol

Surely by the same logic upvoting without providing a reason for it should also be decentivised - why should negative feedback require taking the time to explain "why", whilst positive feedback would not - logically either they both require a "why" or none does.

An uneven posture when it comes to receiving feedback only makes sense if one is emotionally impacted by "somebody disagreed with me and didn't told me why" and having such a socially fragile ego is really the problem of that person, not of everybody else.

More generally and as I pointed out in a long post which I made in the other Karma thread (which I will not repeat here), the removing (or punishing) downvotes is just a strategy to incentivise more content posting, no matter how mediocre, which in turn leads to a a lower signal to noise ratio (i.e. more mindles fluff less content) which is bad for everybody - no-work negative criticism (i.e. downvotes without the need to spend time making explanatory posts) are quite an effective way of providing feedback on the shoddiness of something without the artificial barrier against criticism which is to require spending time on an explanation - I mean, if 1 or 2 downvotes get to you, then you definitelly have emotional issues you need to explore with an expert in such things as a handful of anonymous "I don't like that" can be easilly dismissed as "there are a handful of people who disagree with what I wrote (so what?!)", whilst an unexpected 10 or 20+ downvotes are often a pretty good hint to think again about what your published.

It seems to me that it's incredibly selfish and self-centred to demand that everybody else takes the time to write an explanation when you write something they disagree with: other people's time is their own and they do not exist merelly to serve your ego just as you don't exist merelly to serve theirs.

Mind you, I do think it would be fair for there to be some way for people to disable viewing of downvotes on their account, as people with such "sensitivity" to negative feedback deserve to be able to participate in social media just like everybody else and since Lemmy keeps track of both negative and positive votes getting the interface to just show the positive stuff should be reasonably easy and it would protect the ego of those who need such protection.
I think the idea of sacrificing your own “good boi points” to downvote a post bring a new layer of complexity. For sure, the hive-mind effect would be attenuated if users had to sacrifice their own “points”, and, probably, the downvoting as a whole would be less used. What do you guys think about how the use of the downvote would change?
- Oh I doubt anyone would implement that as a system, but it is interesting to speculate what it might change. Imagine all the downvote curmudgeons having to regularly post pictures of kittens to /c/aww in order to recharge their karma.
  
  I rarely downvoted on Reddit because I’m pretty sure everyone (no matter how blasé they appear to be) gets more upset by a comment ending up at -1 than they would get pleased by it ending at +5. When I found that some instances here don’t even have the downvote button, I decided that I wasn’t going to use it here at all. If someone says something damaging to the conversation I’ll report it to the mods, if they say something factually incorrect I might correct them, but otherwise I will just move on.
I do like that. Perhaps an exponential factor where if you downvote 10 comments you lose 1 karma, downvote 20 you lose 10 karma, etc.
- I see the hivemind disagrees :-)

User scores are bad. Up/downvotes are bad.

The whole point of them was to create a flow of content with minimum human intervention. That’s a huge goal and The Dream if you’re making money off social media. If you’re not making money off social media then it’s not doing you any good.

Abolish karma, abolish comment and post scores.

I say we make them invisible but still keep them for backend. Same with karma.

Besides base thresholds to prevent bots, it could also be used in mod recruitment to make sure mods are active members of a given community. As Lemmy evolves other useful mod tools could also leverage those scores. Perhaps by giving either limited moderator powers or enhanced reporting powers to a communities most active members.

I fully agree that karma/vote-scores are contusive to creating toxic hive mind environments, but I think their visibility is the crux not their existence.