The tweet quickly appeared to become his most shared ever, racking up more than 887,000 retweets and 1.6 million likes by late Friday afternoon, according to social media analytics company Tweet Binder and researchers.
“The fact that Donald Trump broke the info on Twitter indicates that this is his mode of choice for communicating with the American people about the most serious things,” said Samuel Woolley, a professor and director of a propaganda research team at the University of Texas at Austin.
Trump has one of the most popular Twitter accounts in the world, with 86.6 million followers. He uses the site to broadcast his thoughts on issues, promote his campaign for presidency and attack his critics. Even as Twitter invoked Trump’s rage earlier this year by slapping fact checks and labels on his tweets, Trump kept tweeting multiple times each day.
That’s unlikely to stop during his quarantine, especially if his symptoms remain mild, social media experts who follow his account say. It may even give him more time to tweet. Trump has been known to tweet more during times of rest or travel over the past few years, Woolley said.
“I bet that once he has his feet under him, assuming his case is relatively mild, he’s going to be tweeting more than ever,” said social media researcher and Clemson University professor Darren Linvill.
It’s not just the president. Shelter-in-place and quarantine restrictions this year have proven that people turn to social media more often when they’re stuck inside. In the early weeks of the pandemic, Twitter reported that its number of daily users increased 23 percent from the year before to 164 million people.
Other world leaders have already set an example for how to manage social media while battling the coronavirus this year. When British Prime
An aspect of video calls that many of us take for granted is the way they can switch between feeds to highlight whoever’s speaking. Great — if speaking is how you communicate. Silent speech like sign language doesn’t trigger those algorithms, unfortunately, but this research from Google might change that.
It’s a real-time sign language detection engine that can tell when someone is signing (as opposed to just moving around) and when they’re done. Of course it’s trivial for humans to tell this sort of thing, but it’s harder for a video call system that’s used to just pushing pixels.
A new paper from Google researchers, presented (virtually, of course) at ECCV, shows how it can be done efficiency and with very little latency. It would defeat the point if the sign language detection worked but it resulted in delayed or degraded video, so their goal was to make sure the model was both lightweight and reliable.
The system first runs the video through a model called PoseNet, which estimates the positions of the body and limbs in each frame. This simplified visual information (essentially a stick figure) is sent to a model trained on pose data from video of people using German Sign Language, and it compares the live image to what it thinks signing looks like.
Image Credits: Google
This simple process already produces 80 percent accuracy in predicting whether a person is signing or not, and with some additional optimizing gets up to 91.5 percent accuracy. Considering how the “active speaker” detection on most calls is only so-so at telling whether a person is talking or coughing, those numbers are pretty respectable.
In order to work without adding some new “a person is signing” signal to existing calls, the