Posey's Tips & Tricks

The Bounds of Facial Analysis Tech in the Age of Video Calling

Sophisticated facial analysis tools, powered by machine learning, are already on the market. Let's hope they don't make it into your next Microsoft Teams or Zoom meeting.

One of the side effects of all the chaos of 2020 is most of us are now attending way too many online meetings.

I've always thought of online meetings as being roughly analogous to in-person meetings, but with one exception: Online meetings give participants the ability to become "invisible," just by turning off their video feed. Once the camera is off, participants can do whatever they want and nobody is any wiser.

I have to confess that I am one of the worst offenders. Thanks to a wireless headset, I once attended an online meeting while outside, on a ladder, cleaning my gutters.

But soon, it may not be quite as easy to goof off -- I mean, multitask -- during an online meeting. I have been hearing rumors that some online meeting platforms are coming up with creative ways to tell who is paying attention in an online meeting and who is not.

The technology to figure out who is and isn't actively participating in online meetings has actually been around for a while. Consider the ON24 platform that many organizations use when hosting webinars. ON24 actually calculates an engagement score for webinar participants that can be used to tell who is and isn't actively engaged at a given moment.

Of course, webcams could potentially be paired with machine learning technologies to create even more in-depth behavioral analytics.

I'm reminded of the time a few years ago -- around 2011 -- that my sister showed me her new digital camera. Unlike every other digital camera I had seen up to that point, my sister's fancy new high-tech camera had integrated facial-gesture capabilities. For instance, it could tell whether someone was smiling or blinking while a picture was being taken. Today, such features are commonplace, but back then they were relatively unheard-of.

I tell this story to illuminate the fact that technologies capable of analyzing facial expressions have been around for at least a decade. Such capabilities have only been enhanced by modern machine learning algorithms such as those used by Amazon's Rekognition.

With that in mind, imagine what an online meeting provider could potentially discern about a participant just by using the person's webcam feed. An embedded algorithm might be able to use facial expressions to detect boredom, distraction or perhaps even disdain. Think about that last one for a moment. Imagine a boss using technology to figure out which employees like his ideas and which find those ideas completely off-putting.

My point is that existing facial expression monitoring technology could easily be adapted to tell whether someone is paying attention in an online meeting, but that same technology can also turn the meeting provider into the thought police by tracking employees' emotions. Even though this all sounds like something out of a bad late-night sci-fi movie, the technology already exists.

It remains to be seen what the future holds regarding online meeting platforms ratting out employees to their bosses for not paying attention, committing thought crimes or other infractions.

On a much brighter note, however, there is always the possibility that online meeting providers will make a conscious decision not to use technology as a way to make meeting participants' lives miserable. In fact, it is already starting to happen.

Zoom once pioneered attendee attention tracking, but has since reversed course. Initially, it was able to alert meeting organizers if attendees clicked away for more than 30 seconds. More recently, however, Zoom announced that it has done away with its attention-tracking feature because of privacy concerns.

Let's hope that covert facial analytics are never integrated into online meeting platforms.

About the Author

Brien Posey is a 19-time Microsoft MVP with decades of IT experience. As a freelance writer, Posey has written thousands of articles and contributed to several dozen books on a wide variety of IT topics. Prior to going freelance, Posey was a CIO for a national chain of hospitals and health care facilities. He has also served as a network administrator for some of the country's largest insurance companies and for the Department of Defense at Fort Knox. In addition to his continued work in IT, Posey has spent the last several years actively training as a commercial scientist-astronaut candidate in preparation to fly on a mission to study polar mesospheric clouds from space. You can follow his spaceflight training on his Web site.

Featured

  • Microsoft and SAP Enhance Partnership with Teams Integration

    Microsoft and SAP this week described continuing partnership efforts on Microsoft Azure, while also planning a Microsoft Teams integration with SAP's enterprise resource planning product and other solutions.

  • Blue Squares Graphic

    Microsoft Previews Azure IoT Edge for Linux on Windows

    Microsoft announced a preview of Azure IoT Edge for Linux on Windows, which lets organizations tap Linux virtual machine processes that also work with Windows- and Azure-based processes and services.

  • How To Automate Tasks in Azure SQL Database

    Knowing how to automate tasks in the cloud will make you a more productive DBA. Here are the key concepts to understand about cloud scripting and a rundown of the best tools for automating code in Azure.

  • Microsoft Open License To End Next Year for Government and Education Groups

    Microsoft's "Open License program" will end on Jan. 1, 2022, and not just for commercial customers, but also for government, education and nonprofit organizations.

comments powered by Disqus