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

Show HN: Using stylometry to find HN users with alternate accounts

stylometry.net

Post reply on HN
Print view View original

201–210 of 562 posts

Re: Show HN: Using stylometry to find HN users with alternate accounts

#201

Post by birdyrooster »

tbrownaw wrote: post #159
jsnell wrote: post #105

After a few tries on boring accounts, I thought to try the account of somebody who was notorious for an incident outside of HN, and had a (deservedly) bad time at HN for a couple of years before the account went dark. And yeah, there's a bunch of high confidence (.6-.8) hits for that account, and from a quick browse of the comments of the recently active ones, they look really likely to be alts. Like, all three that…

> but this functionality turned out way creepier than I thought the moment I tried it Hopefully this raised awareness means that people who actually need anonymity will be more likely to know to take precautions.

No post body was provided.

Re: Show HN: Using stylometry to find HN users with alternate accounts

#202

Post by bhaney »

drc500free wrote: post #155

This is a super interesting tool for self reflection. Looking at the top 10 similar accounts to mine, it gives me an arms-length view of how other people probably interpret my tone. I appear to be a well-educated, over-confident know-it-all.

> I appear to be a well-educated, over-confident know-it-all.

Don't we all?

Re: Show HN: Using stylometry to find HN users with alternate accounts

#203

Post by costco »

jsnell wrote: post #137
sillysaurusx wrote: post #127

Earlier quoted context omitted.

The explanation is here: https://news.ycombinator.com/item?id=33755466 As far as I’m concerned, it’s the killer feature of the app. The top 20 results may be noisy, but the bolded results have a signal to noise ratio close to infinity.

The precision of the bolded results looks like maybe 30% to me. Significantly better than the non-bolded, but nowhere near perfect precision.

False positives become an increasingly difficult problem the more and more potential authors you introduce. If I had wrote a fancier model it probably wouldn't be as much of a problem but what can you do.

Re: Show HN: Using stylometry to find HN users with alternate accounts

#204

Post by Ros2 »

I interviewed years ago with someone who let me know that they use a pseudonym as an employee and their chosen name even got posted as the author for articles they wrote for the company. They were very concerned about their privacy.

I know their blog, which is their HN username, and this tool found their other account.

Perhaps ironically, this person stood out a lot because of this and I didn't forget them.

Re: Show HN: Using stylometry to find HN users with alternate accounts

#206

Post by philosopher1234 »

the_cat_kittles wrote: post #24

pretty cool- i think there should be a term for two accounts that have each other as the top most similar account. kinda sad i dont have one :(

We’re pretty close me and you — closer than my actual alts

Re: Show HN: Using stylometry to find HN users with alternate accounts

#210

Post by carewell »

culi wrote: post #169

Similar to how they make adversarial fashion[0][1] in order to not be tracked by face id AI, I wonder if we can make adversarial stylometry tools to run your comments through in order to anonymize it .. [0] https://hackaday.com/2022/10/20/render-yourself-invisible-to... .. [1] https://adversarialfashion.com/

OP links to a paraphrasing tool on their website.
Post reply on HN