Comment by 542458 | Hacker News Reader

Comment by 542458 | Hacker News Reader

I don't think this post means as much as people are acting like it does.

The indicators of being a spambot they have in their post seem VERY iffy to me. "Not tweeting in the past 120 days", "Location set to a non resolving location", "Small number of followers", "default profile image", "No URL in bio or non-resolving URL in bio", "Not on many lists", "tweets in a different language than the person they're following" - Those all seem like extremely weak signals to me. My profile matches 6 of those, and I'm a human. I would like to see them hand-verify a subset of their results and see if their algorithm matches reality.

Also note that they define "active" differently than Twitter. They define "active" as having tweeted recently. Twitter gives spambot numbers as a percent of monetizable daily active users. I wonder if Twitter's given bot numbers are low because bots don't typically lurk or load ads. I can believe that the total bot count as a percentage of users or as a percentage of recently-tweeting-users is higher than 5%, but that only 5% of daily visitors seeing ads are bots.

> Location set to a non resolving location

This is a terrible metric. Real people use the location field for all sorts of non-location purposes, as well as more freeform descriptions of their location that wouldn't resolve mechanically.

And I don't see a reason why a bot/fake account wouldn't set a real random location.

If I were a bot, I would simply set my location field to "bot/fake"

> My profile matches 5 of those, and I'm a human.

Just out of interest, imagine you were in a hot desert. There is a tortoise in front of you. You reach down and you flip the tortoise over on its back. The turtoise lays on its back, its belly baking in the hot sun, beating its legs, trying to turn itself over but it can't, not without for your help. But you're not helping. Why?

... I'll tell you about my mother.

I've seen things you people wouldn't believe... Tesla Roadsters on fire off the shoulders of Orion.

Does it please you to think that I am not helping. Why?

Because that tortoise is a politician.

The tortoise is fine. You think it's never been on its back before? There's a thing called resonance that lets it's get back on its feet.

The real question is how strong am I to flip a hundred fifty pound tortoise without injury?

My main account until recently would have qualified as a bot by those criteria until recently.

Meanwhile, several accounts of mine that were predominantly run with bots would have passed as human with ease when they were active.

My main account literally has “fake account” in the description as sort of a joke, because I really use Twitter exclusively for browsing, and maybe liking/RT’ing stuff.

> ... until recently ... until recently.

Are you sure you aren't a bot?

Hah! A good bot wouldn't get distracted and edit a line without reading it all back to make sure it still made sense ;)

I guess I'm a spambot too.

But hey maybe with these kind of analysis, and rando computer generated / un-appealable bans in the the future the "real accounts" will just mean "very elaborate bot".

I think I match all of them and I too am a trustworthy human, fellow human.

Exactly what a bot would say.

hah ha, fellow human, how we love to jape!

I think i match all of this. Also, a simple user account with an URL in bio is definitely more sketchy in my eyes than one without.

That seems like most accounts. I know many real people with exactly those properties.

Also,

Bots tweet and they usually have some sort of generic profile picture, so their methodology wouldn't even account for real bots. Bad.

Regardless, I do think that there are a lot of bots in TW and they are definitely more than 5% of total users.

Yup. Imagine the disdain there'd be on this forum if Twitter used these signals for policy enforcement and somebody was hit by a FP.

"WTF, my account was closed because I didn't tweet in four months."

Mine as well. I deliberately have not set a profile image, and have not attracted many followers. I probably should not bother with Twitter but I am around and am a real human.

They did mention that no one feature was a clear indication of being a spam account, but rather a combination of them.

I match these as well, though I'm not an active user.

The opposite is also true, it misses a lot of real bots.

Seriously. Having a URL in your bio is suspicious IMHO.

Reply on news.ycombinator.com