Hey! Thanks to the whole Reddit mess, I’ve discovered the fediverse and its increidible wonders and I’m lovin’ it :D
I’ve seen another post about karma, and after reading the comments, I can see there is a strong opinion against it (which I do share). I’d love to hear your opinions, what other method/s would you guys implement? If any ofc
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.
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?
Maybe something akin to Reddit’s award system as a way to thank people for being positive contributors? I think that could also be gamed but a way to say thank you rather than a status symbol meaningless number I think is a net positive.
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.
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
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.
deleted by creator
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
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.
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.
Ah, I see. That makes sense.
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.
(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.
That real question is, what problem are we trying to solve? Then we can go from there.
Good point, take my:
handshake, pat on the back, slightly too long hug point thingy.
Number go up, makes brain happy
Number go down, makes brain sad ;(
Monkey sees negative numbers, neuron activation, monkey leaves Lemmy
Monk tap where Apollo used to be on phone. Monk end back up on lemmy
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.
Some kind of implementation of what you said would solve Reddit’s problem of mods reposting and deleting content untill it “goes viral”.
The exciting thing about this space is that much of it is undefined. It is all about the protocols and the main features at the moment. The 2nd generation tools will be born out of what we discuss now and think about now.
How do you make sure a user is not trapped in his special interest bubble and still gets to see content that has everyone excited? How will we make use of the underlying data, on both posts and users to suggest and aggregate content.
I think there will be more than one solution eventually, different flavours of aggregators running on the same underlying data.
So much possibility. And we control it. If you don’t like the way your lemmy instance or kbin aggregates, choose another site or build your own. The data is there.
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.
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.
Exactly this. You want to incentivize discussion, not the dopamine rush casino/arcade that just leads to low effort, low quality posts. If people want to be here for discussion, then they will either lurk and consume, or participate earnestly. Don’t put systems in place that reward the opposite.
I am not sure I followed, sorry
Basically they only want autistic levels of Internet “debate” and don’t want people having low effort fun.
-
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.
It’s a definitely an area to watch but I’m a huge believer that transparency makes a community better regardless of size. If you being brigaded or abused it’s visible to everyone and you can block those accounts if you wanted
The ultimate hope is that social media evolves for the better
On the one hand yes, but also, this makes it much less incentivizing to downvote instances of abuse, discrimination, far right extremism. A lot of those people are not okay mentally and hiighly committed to harassing anyone who disagrees with them, I constantly hear stories of a single disagreement leading to years of harassment on hundreds of alts.
You sound like a normal person who doesn’t take shit personally – some people really, really do take negative feedback on social media the way that you might someone keying your car, and I worry about the repercussions of downvoting the 'wrong" person who might seek reprisal. An anonymous downvote button feels like an “oh, fuck off” button, a public one feels like “fuck YOU for real” to me.
Well said there’s probably more of a barrier without the anonymity which in itself can be also unhealthy for the whole system (less user engagement). Though now thinking about it maybe that’s not a bad thing. Less bandwagoning on downvotes etc.
But truely angering some unhinged lunatic by downvoting who will then dox you, harass you and possibly kill you doesn’t sound great. But that’s a danger you’re susceptible to just by existing on internet.
-
In wondering about that myself. What is the problem?
Individual users having some sort of reputation is useful. I always thought it was handy on Reddit to be able to distinguish people I happened to disagree with from actual trolls. The latter always had pretty high negative karma scores, and it was good to know that there was no point in engaging with them.
Or you could have a system where trolls and bad people are simply banned in stead of needing users to figure it out themselves
The thing is, high karma on Reddit doesn’t mean someone has a history of thoughtful engagement. Just as often, if not more, it means someone whose well timed with zingers on popular posts.
And incentivising that kind of take-down behaviour actually creates toxic communities.
I agree with you that high karma doesn’t indicate anything besides popularity, but someone with negative karma is almost certainly either a troll or a political extremist of some sort. I do find it useful to know when I would be better off not engaging with people like that.
This is why it’s useful at the account level. It’s also useful at the post level in order to build a sorting algorithm which raises the most engaging/important/interesting submissions to the top. Within a community it is important to help define what that community is - irrelevant and low effort content is suppressed and relevant/high-effort gets boosted. Moderators can enforce this by just removing and pinning too, but that’s almost always too unilateral, and the voting system is generally better because it’s expected that then you get a representation of how people in that community feel about it. It’s a good system.
I can imagine some tweaks to help improve how karma is implemented:
-
Use Bayesan Inference to produce a ‘shit/shinola score’ for contributors instead simple up/down vote totals
-
Experiment with different recency biases for the score; you can trust that people will change over time
-
Generally figure out what you’ll be using karma for and make sure you have a way to measure how well it’s working
I’ve googled Bayesan Interference, however I don’t understand what you meant by it. Could you elaborate please :)
Here is a good general explanation of Bayesian inference.
I think @[email protected] is suggesting using such techniques to predict “troll” or “not troll” given the posting history/removed comments/etc. My personal thought is that whatever system replaces karma, it should be understandable to the typical user. I think its possible Bayesian inference could be used in developing the system, but the end system should be explainable without it.
Thanks for the link. To anyone that does’t know about Bayesian inference, do check it out!
Now I have an existencial crisis thanks to the video 😂 the funny part is that thats the same thing used to detect spam email…
-
You can check their post history? Karma doesn’t tell you anything, really. Mine went up tenfold one day just because I replied to what ended up as the top post in a top thread in a much bigger sub than those I normally post in. Some people spend all their time in big subs making short, smart remarks that get a lot of karma, others spend their time in enemy territory battling people they disagree with. Some toxic people have a lot of karma because they hang out in toxic subs.
The problem to be solved is how to order threads. Old skool bulletin boards just bump the most recently replied one to the top. Which works well on an old skool bulletin board as long as it isn’t too large, but very badly on a big site where a few big active threads can drown out all the others.
I don’t know what the solution is. But the numbers don’t mean anything without checking the context. Karma is useful for ordering threads/comments, and giving users a bit of dopamine when they get some attention. But there (probably) are better ways to do it.
I don’t even know that karma/upvotes are good for ordering threads or comments. It just encourages gamification, group think, and snark.
I’d say get rid of down votes, replace upvotes with emoji reacts, and sort based on reacts + replies, but that’s probably just encouraging gamification, group think, and snark, too.
Reddit, like other centralized social networks that are trying to monetize us, prioritizes time on site and generic “engagement”. Those are what generate the most money for the company.
They’re not what’s best for us as users.
Maybe what we need to do is allow users to quickly and easily hide comment chains - not just collapse them, but dismiss them entirely - and allow for user-scriptable and shareable sorting algorithms. We drop down votes entirely, because they’re just used passive-aggressively anyway, make blocking users as easy as possible, with temp blocks and notification silences at the ready, and then forget about user reputation points entirely, because they’re as meaningless as Dragonball Z power levels.
Good stuff, thanks.
Repetitive low-effort posts and comments were common on Reddit
That it true… if they don’t “earn” anything for low effort comments, then they will diminish
They very often get hundreds, if not thousands, of upvotes, though.
They’re common on the internet and real life in general.
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
A web of scores works, but it’s not easy to implement at scale. It means that you’d assign a quality score to people, and in turn would get scores through that person for people you don’t know. If you value somebody highly, you value the people they value.
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.
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.
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.
