Skip to main content

Bot or not? A.I. looks at Twitter behavior to sort real accounts from fake

For the past several years, there’s been heightened concern about the impact of so-called bots on platforms like Twitter. A bot in this context is a fake account synonymous with helping to spread fake news or misinformation online. But how exactly do you tell the difference between an actual human user and a bot? While clues such as the use of the basic default “egg” avatar, a username consisting of long strings of numbers, and a penchant for tweeting about certain topics might provide a few pointers, that’s hardly conclusive evidence.

That’s the challenge a recent project from a pair of researchers at the University of Southern California and University of London set out to solve. They have created an A.I. that’s designed to sort fake Twitter accounts from the real deal, based on their patterns of online behavior.

“Detecting bots can be very challenging as they continuously evolve and become more sophisticated,” Emilio Ferrara, research assistant professor in the USC Department of Computer Science, told Digital Trends. “Existing tools that work well with older and simpler types of bots are not as accurate to predict more complex ones. So it’s always exciting to identify new, previously unknown characteristics of the behavior of human users that are not yet exhibited by bots. This could [be used to help] improve the accuracy of detection tools.”

The researchers leveraged various datasets of hand-labeled examples of both fake and real Twitter account messages, produced by other researchers in the community. In total, they trained their system on 8.4 million tweets from 3,500 human accounts and an additional 3.4 million tweets from 5,000 bots. This helped them to uncover a variety of insights into tweeting patterns. For instance, human users are up to five times more likely to reply to messages. They also get increasingly interactive with other users over the course of a long Twitter session, while the length of an average tweet decreases during this same time frame. Bots, on the other hand, show no such changes.

But don’t expect this work to be the definitive lasting word in this field. Just like the cat-and-mouse game between software companies and hackers, whereby one group tries to close vulnerabilities and the other works to find new ones, the field of bot discovery will continue to develop.

“These findings will inform future bot detection tools,” Ferrara said. “However, we expect that bot-making tools will see these findings as well, so it will be interesting to see when — or how soon — some of the open-source bot-making tools that are available online will adjust to reflect the human behavioral trends that we discovered.”

A paper describing the work was recently published in the journal Frontiers in Physics.

Editors' Recommendations

Luke Dormehl
I'm a UK-based tech writer covering Cool Tech at Digital Trends. I've also written for Fast Company, Wired, the Guardian…
Intel goes to war with Nvidia and Qualcomm
An AI recreation of Intel's co-founder, Gordon Moore.

"Whatever has been done can be outdone, and in ways we haven't imagined yet." Those were the words that Intel chose to open its Computex 2024 keynote with, and those words were spoken by the AI version of its co-founder, Gordon Moore.

Intel stands by the words of its co-founder, though, while some big names in the tech space disagree -- such as Nvidia CEO Jensen Huang. Huang has been pretty vocal about his belief that Moore's Law is no longer practical, going as far as to say that "Moore's Law is dead" in 2022. Now, not for the first time, Intel CEO Pat Gelsinger fired back with another take on the matter.

Read more
Intel’s next-gen Arrow Lake may introduce some major changes to desktop chips
Intel CEO Pat Gelsinger presents Intel's roadmap including Arrow Lake, Lunar Lake, and Panther Lake.

It's been a busy Computex for Intel, but one of its most exciting announcements -- at least for consumers -- slipped a little under the radar. The company will soon expand its portfolio of desktop processors with the next-gen Arrow Lake, and we now have a rough idea of when CPUs will hit the market and how much of an improvement we can expect. Interesting bonus: Some of the new Z890 motherboards will support CAMM2 memory.

According to Wccftech, Intel is planning to officially unveil Arrow Lake in September during the Intel Innovation event, and the processors will launch shortly after, sometime in October this year. Desktop users are the lucky ones here, as they're the ones who will get access to Arrow Lake first -- laptop chips will follow at an undisclosed date. However, laptop users already get plenty to sink their teeth into with this year's Lunar Lake.

Read more
Microsoft is backpedaling on future Windows 10 updates
The Windows Update screen in Windows 10.

Windows 10 is on its way out, with support ending in October 2025. That isn't changing, though Microsoft's approach to rolling out new features in the meantime definitely has. In a surprising move, Microsoft announced in a June 4 Windows Insider Blog post that it is bringing a Beta Channel for those Windows Insiders currently running on Windows 10 version 22H2.

This means that despite the end of support, Windows 10 users will continue to get some new features that were initially restricted to Windows 11, such as the new Copilot app. It's also possible that other features may be on the way, but Microsoft has not released any further information on the subject. It was originally stated that Windows 10 version 22H2 would be its final feature update, but that appears to not be true anymore.

Read more