Slashdot Mirror
Deep Neural Networks for Bot Detection (arxiv.org)
From a research paper on Arxiv: The problem of detecting bots, automated social media accounts governed by software but disguising as human users, has strong implications. For example, bots have been used to sway political elections by distorting online discourse, to manipulate the stock market, or to push anti-vaccine conspiracy theories that caused health epidemics. Most techniques proposed to date detect bots at the account level, by processing large amount of social media posts, and leveraging information from network structure, temporal dynamics, sentiment analysis, etc. In this paper [PDF], we propose a deep neural network based on contextual long short-term memory (LSTM) architecture that exploits both content and metadata to detect bots at the tweet level: contextual features are extracted from user metadata and fed as auxiliary input to LSTM deep nets processing the tweet text.
That should be a pretty high ranking flag in the algorithm seed data.
Putting way to much confidence in bots ability to do any of those things listed in the summary.
On the Oregon Cost born and raised, On the beach is where I spent most of my days
The standard soultion.
I can't figure it out, so let's throw AI at it.
Look bots are easy to detect. They all have tells and signatures. Just like humans, why because humans wrote them. If you want to detect a bot on the first tweet, all you need to do is think like a programer, and think how would I send out a tweet to 1 million people, without anyone knowing that this is a bot.
In most cases you can simply look for ambiguous yet targeted langage. And example would be "hey look at this cool ".
Another example is links that are not explained in the message.
Another example would be copying a known headline and changing the data in a predictable way. " gets with ".
Note if you or someone you know posts like this, then my firend you have a human bot at work.
How does this resolve the case of my political uncle posting extreme ideas every week or two.
Anyone outside the family would rightfully think he's a bot. He isn't, he's just that uncle.
The first amendment protections required for a system like this would make it far too cumbersome for practical use. Yea, Twitter is proving the opposite case with their manual interventions, but there must be a middle ground
What a great way to silence opposition. They only issue is that most people will simply go to a different website that isn't being censored. You'll have to go deeper!
LTSM has been a pretty good technique for generating / predicting sequential data (generating sentences, recognizing natural language phrases..) so it would make sense that it would be used to analyze behavior (sequential posts on social media) to determine botness.
Now all you gotta do is couple it with an adversarial generator bot thats trying to outwit it, and you have the classic training pair.
Antagonistic neural networks improves the quality of both networks.
The detector will get better and the fake will get better. Quickly.
She was like chocolate when she drank... semi-sweet at first and then increasingly bitter.
I always suspected that about CowboyNeal. Now we will know the truth.
detecting bots, automated social media accounts governed by software but disguising as human users
The expression "bot" is used to describe a wide variety of software applications, not just those emulating people in social media. In fact, the most common bots are the ones used by a big number of sites to retrieve information from internet for different purposes (e.g., search engines retrieving what they are showing to their users); they are also called crawlers or spiders. Here you can find a detailed list of active ones (I am the proud father of one of them :)).
So, a better version of the summary would have been:
detecting the social media bots disguised as human users
Custom Solvers 2.0 = Alvaro Carballo Garcia = varocarbas.
Else, get fucked. Until companies are held responsible - to the degree they bow before libtards - none of this will change. That is kind of the point.
The article is pure clickbait. Just because there's no direct financial link between stolen identities doesn't undermine the importance of securing them. That is all we're being led to believe though. That financial implications are the only worry we should have. Fuck that.
We can't even drag the CEO's behind absolutely disgusting hacks like Equifax to jail, how in the world are we going to deal with smaller hacks like those that hit Bell Canada?
Oh right, 13 Russians are all we should worry about. No.
The answer is NOT more monitoring. It's going after the bastards on Wall St., Bay St., and any other place they hang out.
Easy, isn't it?
Sent as ripples into the electromagnetic field. No single photon has been harmed in the process.
This looks like it will be ideal to create an one half adversarial generative network. Plug a spam bot into the other side and before we know it the spam bots will be even more convincing. Yay :-(
You don't need deep neural networks when this will do:
egrep 'MAGA|NO COLLUSION||FAKE NEWS|LIBTARD' > /russian_bots.txt