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

41–50 of 72 posts

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

#41

Post by SllX »

user3939382 wrote: post #37
23B1 wrote: post #32

I guess I don't understand what the problem is with the current way of doing things? Like, HN is one of the few communities online now where the content and the conversation seem interesting, varied, and polite. Whats the core problem you're trying to solve here?

My biggest gripe, which may not be solvable and isn’t unique to HN, is this vote/point system that ends up as “truth by consensus”. Controversial opinions, which may actually be the correct ones, are hidden and buried and even have their text slowly disappear and fade out which I think is ridiculous. It promotes groupthink and encourages users to just repeat mainstream opinions.

Not as much as you may think.

“showdead” is a feature if you have enough karma and it’s usually easy to see why something is dead.

Controversial arguments made well, or at least to the best of your ability that fall within the guidelines can and do get upvoted. A lot of the dead comments I see are really just ad hominem attacks or near enough to it.

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

#42

Post by jnakayama »

cycomanic wrote: post #38
23B1 wrote: post #32

I guess I don't understand what the problem is with the current way of doing things? Like, HN is one of the few communities online now where the content and the conversation seem interesting, varied, and polite. Whats the core problem you're trying to solve here?

I can tell you one issue I observe as someone living in a different timezone. HN ranking highly depends on timing. As a consequence during hours the US is asleep my impression (I have not investigated this thoroughly) is that front page stories are dominated by old stories and new submissions don't make enough votes to get to the front page. Then once the US wakes, New stories get enough votes and make it to the fron…

If you're interested in investigating timing effects: We collected a dataset last year where we took a snapshot of the newest 1500 stories on HN every minute for several months which should contain the information required. Feel free to play around with it and get in touch with us if you find something interesting!

[1] Dataset: https://osf.io/bnysw/

[2] Exploratory analyses: https://github.com/social-protocols/hacker-news-data

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

#43

Post by chasebank »

23B1 wrote: post #32

I guess I don't understand what the problem is with the current way of doing things? Like, HN is one of the few communities online now where the content and the conversation seem interesting, varied, and polite. Whats the core problem you're trying to solve here?

The only problem I have with HN is the endless content. I wish you could say, 'Show me stories that reached the front page', then hide or watch each story as you deem. That way I could clear out the front page like I do my inbox.

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

#44

Post by jwarden »

sokoloff wrote: post #40

There's a related question of "what's the purpose of the ranking algorithm?" Is it to ensure that the #1 article is strictly "better" (via whatever function) than the #2 and the #2 better than the #3? Or is it to ensure that at least N of the top 30 (page 1) submissions will tend to be interesting to many users on the site (driving engagement and discussion)? As a user, I'm a lot more interested in the second goal th…

I would say the ranking algorithm has many purposes. Driving quality engagement and discussion, as you suggest, is probably the most important. But I think simply being “interesting enough” to many users is not the goal. I think the goal is to make the front page as interesting as possible. That’s why HN has already out so much effort into ranking algorithms and moderation and why we think it is still worth improving if possible.

We actually haven’t implemented a new algorithm (for reasons discussed in the readme). What you see when you click on our site is the exact same rankings, but with the upvoteRate next to each in addition to the score, which you can click on to see charts with a history of the story’s rank and upvoteRate.

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

#45

Post by mistermann »

JohnFen wrote: post #28
mgraczyk wrote: post #26

Earlier quoted context omitted.

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 defi…

The word "is" is also subjective in this context, since "subjective" is not a binary.

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

#46

Post by jwarden »

23B1 wrote: post #32

I guess I don't understand what the problem is with the current way of doing things? Like, HN is one of the few communities online now where the content and the conversation seem interesting, varied, and polite. Whats the core problem you're trying to solve here?

The problem certainly isn’t that HN content and conversation isn’t good. But that doesn’t mean it couldn’t be better.

The core problem we are teying to solve is that the community sometimes misses out on the opportunity to discuss content that many people would find valuable and that would engender quality discussion.

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

#48

Post by jwarden »

supernova87a wrote: post #34

Are you sure / do you have info that HN doesn't use some kind of "holding pen" for stories to have a fixed amount of time to see if they get a certain % of votes before being kicked down the list? This is a classic problem with forums, and I wonder if HN already has something in place that you might not have factored in (which could then just be tuned better).

I think there may well be some sort of “holding pen” system. But we don’t have the info. We only know what the “raw” ranking formula is. But the actual rankings differ significantly from what the raw ranking formula says. You can actually see the difference in charts on our site. For example: https://news.social-protocols.org/stats?id=35183317

We have noticed that the “raw” rank (black line) will sometimes initially put a story on page 1, while it still has no the actual rank (orange line). But then sometimes the orange line suddenly jumps up. This seems to support the “holding pen” hypothesis.

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

#50

Post by ClapperHeid »

nico wrote: post #8
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…

> It is time that we turn our back in the collaborative filtering algorithms that made social media a hellscape and embrace content-based filtering. Except people deeply care about what other people are doing. That was the whole point of Google’s Pagerank algorithm. So, it might not be what you personally want. But to a lot of people, it’s more important to read/consume something popular (ie. that a lot of others car…

  >So, it might not be what you personally want. But to a lot of people, it’s more important to read/consume something popular...
Count me in the "don't care" group. Which is why I always browse HN by "New" [0]. I neither know nor care which stories have been voted to prominence on the default frontpage, nor how this ranking has been determined. I just want to see what's new and select for myself what looks interesting.

[0] https://news.ycombinator.com/newest

Post reply on HN