Twitter is considering badging bots — “as far as we can detect them”

At today’s Senate Intelligence Committee hearing Twitter CEO Jack Dorsey was asked by vice chair Sen. Mark Warner whether users should have “a right to know” if they are talking to a bot or a human on its platform — to help people better navigate the information they are being exposed to.

Dorsey agreed that “more context” around tweets and accounts is good, but — when pressed by Warner on whether Twitter should have a policy to ID bots vs humans on the platform — he said Twitter is actively considering it, albeit cautioning “as far as we can detect them”.

“We can certainly label and add context to accounts that come through our API,” he continued. “Where it becomes a lot trickier is where automation is actually scripting our website to look like a human actor. So as far as we can label and we can identify these automations we can label them — and I think that is useful context.”

“It’s an idea that we have been considering over the past few months,” he added. “It’s really a question of the implementation — but we are interested in it. And we are going to do something along those lines.”

A bit later in the session, answering questions about fake accounts, Dorsey said Twitter has had more success in identifying inauthentic activity on its platform by using deep learning and machine learning technologies that are focused on identifying “behavioral patterns” — so looking at account behavior across the network — rather than trying to identify where specific accounts are located in real-time.

“We’ve got a lot more leverage out of that in terms of scale vs systems that try and identify fake profiles,” he added.

Dorsey tweeted his opening remarks to the committee — though not literally in real time as he read them out. Which rather underlines the challenge for any future ‘bot or not’ labelling system on Twitter, which would need to sift through scripted activity to try to determine what’s human and what’s machine.