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

The Saltiest Users on HN

hackersalt.com

Post reply on HN
Print view View original

81–90 of 92 posts

Re: The Saltiest Users on HN

#81

Post by howard941 »

Kassius509 wrote: post #68
logfromblammo wrote: post #37

Earlier quoted context omitted.

Agreed. It looks like they went through a dictionary and scored the words on a negativity/positivity axis, and then just took the mean of all the scoring words in a post. I have written posts very much saltier than the ones scored as saltiest by this ranking algorithm, possibly because I didn't use inherently negative vocabulary to express a highly negative sentiment. It's a fun party trick, but its usefulness is lim…

You're spot on. This model is based off a dictionary with scored words! For the curious you can see the dictionary here: https://github.com/sloria/TextBlob/blob/eb08c120d364e9086467... The package used is a pretty popular one called TextBlob. It is nifty for working with unlabeled data like we have with the HackerNews dataset. We really focused our definition of saltiness around being a combination of (subjective + n…

My saltiest comment was reportedly "If taxing price gougers seems stupid you're going to hate the pitchfork-toting mobs." I'm not sure how to work some kind of contextual analysis into it but I'm pretty sure it's something on your to-do list. Good on you for the creative idea and implementation and putting it out here for us to sprinkle salt on.

Re: The Saltiest Users on HN

#82

Post by krapp »

thisisit wrote: post #59

My guess is pg_is_a_butt gets enough salt from his username. But this got me curious. Who are the sweetest users? And what kind of topics generate most salt? This will be interesting because there has been a general trend on HN where people bemoan "HN hates X" with X being cryptocurrency, Tesla, new starts on Show HN.

>And what kind of topics generate most salt?

politics, gender, race, theoretical physics (particularly dark matter) and javascript.

Re: The Saltiest Users on HN

#83

Post by ocdtrekkie »

DanBC wrote: post #42
ocdtrekkie wrote: post #2

The first list is mostly people who I don't recognize, and assume are uncommon posters, where one or two bad comments put them on the "saltiest" list. The other two top lists are more interesting, because while there is a lot of salty people in there I recognize, a bunch of people make the list solely based on total prolific amount of comments. tptacek, of course, as well as literally all of the HN moderators. Appare…

If you have "showdead: off" in your profile you won't see some of those users.

I assumed as much. I've played with what HN looks like with showdead: off from time to time, and relatively happy to trust the moderators and leave it turned on. (I am both glad I have the option to view it though, and glad people who are dead-ed still have the ability to participate. I think HN's system here is quite nice.)

Re: The Saltiest Users on HN

#84

Post by ivahuc »

Zak wrote: post #50
weberc2 wrote: post #16

I'm disappointed at how unsalty my saltiest comments are ( https://www.hackersalt.com/weberc2 ). I'll have to try harder. :/

Direct links just go to the home page, even though that's the URL produced by putting your username into the search box. Rather than say something salty about that, I'll just say what we see here is an excellent example of something that should be based on traditional pages rather than a single-page application. In fact, it seems to be an SPA emulating pages poorly, and I can't imagine why anyone would want to do tha…

Thank you very much for your feedback Zak. Those are totally valid points. We will definitely continue to work on the app and fix the search function and share-ability of urls.

Re: The Saltiest Users on HN

#85

Post by ivahuc »

mixedCase wrote: post #32

May I suggest removing Cantarell from the list of fonts used? The font weight used on this site makes it extremely hard to read.

We will definitely work on improving readability of the app. Thank you very for your feedback. Very appreciated!

Re: The Saltiest Users on HN

#88

Post by Kassius509 »

howard941 wrote: post #81
Kassius509 wrote: post #68

Earlier quoted context omitted.

You're spot on. This model is based off a dictionary with scored words! For the curious you can see the dictionary here: https://github.com/sloria/TextBlob/blob/eb08c120d364e9086467... The package used is a pretty popular one called TextBlob. It is nifty for working with unlabeled data like we have with the HackerNews dataset. We really focused our definition of saltiness around being a combination of (subjective + n…

My saltiest comment was reportedly "If taxing price gougers seems stupid you're going to hate the pitchfork-toting mobs." I'm not sure how to work some kind of contextual analysis into it but I'm pretty sure it's something on your to-do list. Good on you for the creative idea and implementation and putting it out here for us to sprinkle salt on.

TYVM.

This kind of feedback gets me pumped about continuing to work on it.

Re: The Saltiest Users on HN

#89

Post by Kassius509 »

jcfrei wrote: post #36

How is saltiness trained? Are there readily available sentiment analysis tools or did the author train it himself? Anyway, cool and entertaining idea :) PS: not just seeing the saltiest but also the sweetest comments of a person would be nice.

For this version we used TextBlob out of the box with some custom weighting to avoid false positives.

We'll relaunch in about two weeks with an improved model that we're currently training on a much larger labeled dataset and SOTA BERT model. :)

Re: The Saltiest Users on HN

#90

Post by Kassius509 »

thisisit wrote: post #59

My guess is pg_is_a_butt gets enough salt from his username. But this got me curious. Who are the sweetest users? And what kind of topics generate most salt? This will be interesting because there has been a general trend on HN where people bemoan "HN hates X" with X being cryptocurrency, Tesla, new starts on Show HN.

Actually, username & story titles aren't included in the model. We may experiment with including them in the future but for now we left them out to avoid any undo bias.

Sweetest users is a good question. I'll have to build out that view some time.

Post reply on HN