Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Quality News – Towards a fairer ranking algorithm for Hacker News

news.social-protocols.org

Post reply on HN
Print view View original

21–30 of 72 posts

Re: Show HN: Quality News – Towards a fairer ranking algorithm for Hacker News

#21

Post by jwarden »

unethical_ban wrote: post #19

I would like the HN UI to have a "favorite" button equally accessible to the "upvotes" button. I know favorites are a feature, but they require clicking into the comments. I end up using upvote as a bookmark function, not as a method of approving of a post, because that's easier. As it relates to this post, the HN UI encourages the feedback loop this submission is trying to fix. Put a bookmark icon next to the upvote…

Good point, I hadn't thought that some people are using the upvote button effectively as a bookmark button. Interesting idea the unified upvotes+bookmarked view.

And your comment raises the question, what does an upvote mean? Why do people upvote? There may be lots of strange reasons. But whatever upvotes mean -- whether it means people want to bookmark it, or people find it valuable, or people want to bring something they disagree with to the attention of other people -- an upvote is a rough signal of "this should get more attention". The whole concept of a link aggregator like HN only makes sense if we assume that upvotes can be interpreted as a proxy for what people think deserves the attention of other users.

Re: Show HN: Quality News – Towards a fairer ranking algorithm for Hacker News

#22

Post by jnakayama »

MilnerRoute wrote: post #6

I'd like to see these alternate algorithms implemented. The API exists - and isn't that really the only way to ultimately judge if it's better or worse? Another random idea: have the parameters affecting rankings be visible and adjustable with interactive sliders- so you could customize the various weights to try to attain the ideal mix of stories for you. Or does that defeat the purpose. Is the joy of HN in knowing…

We played around with customization options like that (URL parameters etc.), but ultimately decided against it. The reasoning behind it was that a lack of personalization might be a feature not a bug for a news aggregator like HN. One issue that arises with personalization is that it is detrimental to a sense of shared experience and we thought that the global frontpage might be a distinct reason for the sense of community on HN.

This issue was also discussed previously on HN: - https://news.ycombinator.com/item?id=31375092

Re: Show HN: Quality News – Towards a fairer ranking algorithm for Hacker News

#23

Post by kqr »

jwarden wrote: post #20
abecedarius wrote: post #17

Idea: if you know all of a user's votes, you can estimate that they at least glanced over the items up to the lowest-placed one they voted on on the same page. This is a bit more information than "users tend to read higher-placed items following a known distribution" like the formula from your readme. I guess you'd have to be HN to implement this.

Interesting idea. Yes that's probably true. One issue is that a story could appear on multiple pages (top, new, show, etc.), and we don't know where the upvote came from. But I think we could deal with that issue and we might be able to use that as a datapoint to refine the upvoteRate calculation, and we could experiment with adding that to our model.

What percentage do you believe does not come from the front page? Is it big enough to actually be worried about?

Re: Show HN: Quality News – Towards a fairer ranking algorithm for Hacker News

#24

Post by akomtu »

HN needs to separate emotion from reason in upvotes and downvotes. I bet that many readers here confuse the upvote button with "I like it" and the downvote button with "I dislike it" while it should be about "is this comment truthful and informative, does it add something novel to the discussion?"

HN could implement this with a cosmetic change: all upvotes and downvotes would show a form to provide explanation. Those explanations will be reviewed, randomly, to spot emotional users and suspend their voting power for a month or two. As for those who can't be botheted with explaining their voting decision, they shouldn't be able to influence the global ranking. Rage downvoting and hive-mind upvoting will be gone very quickly.

Re: Show HN: Quality News – Towards a fairer ranking algorithm for Hacker News

#25

Post by jwarden »

kqr wrote: post #23
jwarden wrote: post #20

Earlier quoted context omitted.

Interesting idea. Yes that's probably true. One issue is that a story could appear on multiple pages (top, new, show, etc.), and we don't know where the upvote came from. But I think we could deal with that issue and we might be able to use that as a datapoint to refine the upvoteRate calculation, and we could experiment with adding that to our model.

What percentage do you believe does not come from the front page? Is it big enough to actually be worried about?

If it's on rank 1 of the front page, then the vast majority of votes come from the front page. But if it's at rank 90 of the front page, and rank 1 of the new or the best page, then in those cases only a minority of upvotes may be coming from the front page.

If HN implemented this, they would know where the vote is coming from. But on Quality News we could just assume there was an X% chance the vote was from the front page, a Y% it was the new page, etc., and adjust our upvoteRate formula based on that.

Re: Show HN: Quality News – Towards a fairer ranking algorithm for Hacker News

#26

Post by mgraczyk »

PaulHoule wrote: post #5

When my RSS reader shows me an arXiv paper about ML with ‘fair’ in the title I hit the reject button. What is ‘fair’ is subjective and what I want is a feed relevant to my interests (also subjective.) This is 2023 and text classification problems that I struggled with at a startup 5 years ago are now easy and the power of transformer models is obscured by the ChatGPT hype. It is time that we turn our back in the coll…

I don't agree that "fair" is inherently subjective. There are many sensible ways to objectively define fair. For example you could say HN ranking is "fair" if the probability any viewer would upvote that article is independent of its position-history on HN. That is an objective definition that is "fair" with respect to positions.

This and other notions of "fairness" are very common problems in ranking (I used to rank things on Instagram) that have to be addressed, even if you're only doing content based ranking.

Re: Show HN: Quality News – Towards a fairer ranking algorithm for Hacker News

#27

Post by manx »

akomtu wrote: post #24

HN needs to separate emotion from reason in upvotes and downvotes. I bet that many readers here confuse the upvote button with "I like it" and the downvote button with "I dislike it" while it should be about "is this comment truthful and informative, does it add something novel to the discussion?" HN could implement this with a cosmetic change: all upvotes and downvotes would show a form to provide explanation. Those…

I think this boils down to:

- Users upvote, because they want that story to get MORE attention, BECAUSE they agree

- Users downvote, because they want that story to get LESS attention, BECAUSE they disagree

So the intent is still attention control, but the reason is (dis)agreement.

But in the case of HN, the downvote is a moderation mechanism, instead of a community poll. So this might be confusing to the user. Treating downvotes differently, based on a top-level reason (disagreement, violating ToC, false or misleading, not interesting, etc) makes a lot of sense to me.

Re: Show HN: Quality News – Towards a fairer ranking algorithm for Hacker News

#28

Post by JohnFen »

mgraczyk wrote: post #26
PaulHoule wrote: post #5

When my RSS reader shows me an arXiv paper about ML with ‘fair’ in the title I hit the reject button. What is ‘fair’ is subjective and what I want is a feed relevant to my interests (also subjective.) This is 2023 and text classification problems that I struggled with at a startup 5 years ago are now easy and the power of transformer models is obscured by the ChatGPT hype. It is time that we turn our back in the coll…

I don't agree that "fair" is inherently subjective. There are many sensible ways to objectively define fair. For example you could say HN ranking is "fair" if the probability any viewer would upvote that article is independent of its position-history on HN. That is an objective definition that is "fair" with respect to positions. This and other notions of "fairness" are very common problems in ranking (I used to rank…

"Fair" is inherently subjective because, in a vacuum, everyone has a subjective definition of the word. It can legitimately mean many different things, after all. People will choose the definition they read it as according to their own subjective experiences.

I reacted poorly to the use of the word "fair" here, too, because I didn't see how "fairness" really entered into it. Naturally, you can provide a specific definition of the word to make it objectively measurable, but if you use a word before you've said what your definition is, people are going to use the common definition -- and therefore, it's subjective.

Re: Show HN: Quality News – Towards a fairer ranking algorithm for Hacker News

#29

Post by woollyhat »

I think it would be interesting if users could spend their karma on performing moderator actions, perhaps with some sort of algorithmic exchange rate that converts acquired karma into modcoins.

For example, it might cost 1000 modcoins to pin an article to the top of the page for ten minutes. Or perhaps more of a bold change: 2000 modcoins to make the text of your comment glow with a golden hue to make it more noticeable. 5000 modcoins to display an image of Paul Graham at the top of the thread, smiling beatifically at all the comments below Him. And so on.

This would of course be of no interest to users such as myself who habitually generate throwaway accounts and discard them, but I would be curious to see how high karma users would use such a feature.

Re: Show HN: Quality News – Towards a fairer ranking algorithm for Hacker News

#30

Post by layer8 »

akomtu wrote: post #24

HN needs to separate emotion from reason in upvotes and downvotes. I bet that many readers here confuse the upvote button with "I like it" and the downvote button with "I dislike it" while it should be about "is this comment truthful and informative, does it add something novel to the discussion?" HN could implement this with a cosmetic change: all upvotes and downvotes would show a form to provide explanation. Those…

You expect emotional up-/downvoters to be objective and truthful about their up-/downvote motivation?
Post reply on HN