Photo used freely from the excellent Gratisography website |
A professor and student at the University of Alberta's Computer Science Department, Eleni Stroulia and Mashrura Tasnim respectively, have recently released their findings with regards to A.I's depression detecting abilities, and the potential this might have for future applications.
They used data from previous research and, using various machine-learning algorithms, they developed a new way to detect depression in the timbre of a subject's voice. This method might lead to new ways in which our tech can monitor our well-being:
"A realistic scenario is to have people use an app that will collect voice samples as they speak naturally. The app, running on the user’s phone, will recognize and track indicators of mood, such as depression, over time. Much like you have a step counter on your phone, you could have a depression indicator based on your voice as you use the phone." - Eleni StrouliaAs someone who suffers with depression, this kind of news is quite exciting. I don't always catch myself slipping into a bigger 'dip' in mood, and sometimes the realisation only comes once I'm entrenched in cycles of downward thinking. If I had an app on my phone that could pop-up a notification and say "Hey, you are dipping a little!" I might have a chance to get ahead of things and do those self-care things that sometimes help take my thinking down a more cheerful path.
The more I think about it, the more I'm curious as to how A.I might perform in detecting other emotions in our voices. How cool would it be to have a friendly app saying "You're very lonely right now, don't let this affect your standards with your Tinder swipes!" I know that is only a few steps away from HAL and his "I'm afraid I can't do that" attitude, but hey, it's interesting to ponder.
Source: University of Alberta