People who know me know that very little in the tech world gets me excited. I’ve seen so many tech ideas constantly recycled and repackaged from the 2000s, it makes me, well — I hate to admit it — but I’m a little jaded.
So a few years ago, when I first caught whiff of apps for monitoring your happiness in a completely passive manner, I was intrigued.
More researchers are jumping on this bandwagon, and it’s one of the few innovations in smartphone apps worthy of a mention.
The biggest problem with behavioral and mood monitoring smartphone apps is that they suffer from the Achilles heel of nearly all such apps — they require active data input by the user. On a daily or weekly basis, enough so that they bring very little new to the table (given that you can monitor your mood on websites like this one and dozens like it).
Who wants to sit around and tell an app how they’re feeling all the time? That gets annoying really quickly.
Or you simply forget and stop using it. “Oh yeah, there’s that mood app I used for a week 2 years ago.” Delete.
We Need to Build a Better Mousetrap
These first generation apps are downloaded millions of times, and then actively used by less than 1 percent of those who downloaded them past the first month. The attrition rate is so horrible, it drives many app makers out of business.
What’s needed is an app that passively monitors your mood in the background, without any user intervention needed. How do you do this? As I wrote 2 years ago:
Since phones generally only have a limited amount of inputs — voice, video, geo-positioning (GPS), and an accelerometer — your choices as a researcher interested in personal health data are pretty limiting. Using only these four physical measurements, is it really possible to accurately and reliably measure a person’s well-being?
The answer 2 years ago was, “sort of.” The existing research demonstrated some weak correlations suggesting such passive monitoring was possible. But more research was needed.
New Research from the University of Michigan
The new research is being led by computer scientists Zahi Karam, Ph.D. and Emily Mower Provost, Ph.D., and psychiatrist Melvin McInnis, M.D. at the University of Michigan. They presented their first preliminary findings last week at the International Conference on Acoustics, Speech and Signal Processing in Italy. The project is called PRIORI, because they “hope it will yield a biological marker to prioritize bipolar disorder care to those who need it most urgently to stabilize their moods — especially in regions of the world with scarce mental health services.”
That’s a tall order, and it’s hard to understand how after decades worth of genetics research into bipolar disorder, we’re making much progress on finding said biological markers. If anything, the research has demonstrated how truly complex these disorders are.
Nonetheless, the researchers’ app only monitors voice to try and determine mood based upon the amount of speech, sounds, and silence it hears during phone calls. “Only the patient’s side of everyday phone calls is recorded — and the recordings themselves are encrypted and kept off-limits to the research team.”
The first six patients all have a rapid-cycling form of Type 1 bipolar disorder and a history of being prone to frequent depressive and manic episodes. The researchers showed that their analysis of voice characteristics from everyday conversations could detect elevated and depressed moods.
It’s a good start, but as I said two years ago, we need much larger studies to determine if this stuff really has any long-term value.
Given that there are more variables the app could be monitoring — like using most smartphones’ built-in accelerometer — it seems a shame they’re just sticking to voice. And just of one side of phone calls.
I still believe these miniature computers we’re all carrying around to use for simple things like texting and phone calls could be leveraged in ways that we’re only beginning to scratch the surface of. We’re making progress in this area, but it seems slow-going despite the vast technological power we now have available.
Here’s to the 2.0 generation of smartphone mood monitoring apps. I look forward to their arrival in the next few years.
Read the full news release: Listening to bipolar disorder: Smartphone app detects mood swings via voice analysis