Ellie - The robotic therapist

The Black Oil · 13-05-2015 10:38pm #1

Caught a story about this over on the Planet Money podcast.

Searching around, it's not new as it was reported in 2013 and last year. In the story I listened to, one guy work was injured in Afghanistan found her non-judgement in her eyes particularly. The previous link mentions she was originally commissioned by the U.S. Department of Defence.

Maybe this is key

The idea here is not for Ellie to actually diagnose people and replace trained therapists. She's just there to offer insight to therapists, Morency says, by providing some objective measurements.

More at The Economist. Here's a video, hi Ellie. Where would she go for clinical supervision?

https://www.youtube.com/watch?v=ejczMs6b1Q4

The Black Oil · 22-05-2015 6:59pm

Turns out, she can perhaps spot depression too.

"Contrary to popular belief, depressed people smile as many times as non-depressed people," Rizzo says. "But their smiles are less robust and of less duration. It's almost like polite smiles rather than real, robust, coming from your inner-soul type of a smile."

http://www.npr.org/sections/money/2015/05/20/407978049/how-a-machine-learned-to-spot-depression

Torakx · 22-05-2015 9:25pm

I know all about that type of smile. Or for extraverts depressed, the over compensating laugh.
Maybe some types of depression is due to under stimulation.
I find I laugh with peoples jokes as a polite acknowledgment. But notice thatother laugh longer.
It feels like the joke is too simple and not worth laughing. Which makes me wonder if really "boring" people just see allthe punchlines and are just not surprised by apparently random ideas.
My situation more or less has been whatothers might see a negative. My depression probably lost it's grip when I was in the same situation, but had purpose for my energy.

The Black Oil · 03-06-2018 9:40pm

Caught this via the Radiolab podcast - More or Less Human episode. https://www.wnycstudios.org/story/more-or-less-human

Turns out we had Eliza, back in the day.

In 1964 Joseph Weizenbaum started the development of Eliza, a computer program that was able to have a normal conversation with a person. Eliza processed natural language as an input and, as an output, it offered answers as it were a natural conversation between two people. By 1967, using Carl Rogers principles of the psychology of empathy, Weizenbaum had managed to develop a computer program that could converse with a human being in a coherent way. One could argue, this was the world’s very first Chatbot.