31–40 of 90 posts
I have been seeing a woman's posts lately who is going through a bitter, ugly divorce, and it's astounding how she represents everything publicly via Facebook when I know the full story due to a family member being involved.
Earlier quoted context omitted.
They didn't use that as an indicator of depression. All they did was pass into the model the number of faces in the frame. The analysis afterwards suggested that depressed people tend to not have group photos.
Well doh People who don't hang out with other people are more at risk for depression AND they are less likely to have group photos. This is called a latent variable.
Earlier quoted context omitted.
> Or get off social media entirely. Wouldn't that be a bigger red flag?
Red flag of what, though? Eg, I stay away from social media, and create burners for just about everything (rotating burners semi frequently depending on how many random details I post, etc) - so what am I an indicator of? I try to be a Ghost. I'm sure a ghost is an indicator for some things, but the majority of it is just speculation right? I have trouble thinking of how a lack of information about someone could be h…
If your employer/government/etc asks you for your facebook/google+/instagram/snapchat/etc account and you say you don't have any, it might come off as being suspicious. As if you are trying to hide something. The same thing with your banks/financial institutes/etc.
Earlier quoted context omitted.
What kind of tasks were you hired to do on this latter topic?
Tagging scenes Genders in the scene Positions etc... I'm curious how ML will do that, not how but accuracy would be cool to make (train) the model. Also with thumbnails that capture the viewer's attention. The other jobs were brute searching sites in hopes to improve SEO. Transcribing photos of receipts (funny those ads, some poor schmuck being paid 12 cents per 10 min job). Oh I remember an awkward one it was some s…
I'm curious on how this works. Do you basically search for specific keywords and click on specific URLs in order to signal Google that the URL is more relevant?
And in 10 years, this will be a part of your Citizen Score. I should burn this nickname and be more diligent about persona management. Or get off social media entirely.
I'm pretty sure the only reason social media isn't incorporated into credit scoring is that it's too difficult to reliably attach to a given individual without help from Facebook, etc. FB definitely does not want to become a consumer credit reporting agency, so their ability to cooperate without triggering the FCRA is limited.
Earlier quoted context omitted.
Shit, I don't have group photos :(
Do you also have the other markers? It's not like a single marker determines everything. It's not even like having ALL markers means one is 100% depressed. It merely gives you a confidence score in the person being depressed.
TL;DR - If you post a lot of gray pictures of yourself with a sad face that nobody likes or comments on, you are probably depressed. They used the color of the photographs, number of people in the photos, level of engagement, and happiness rated by Mechanical Turk to determine depression.
TL;DR - If you post a lot of gray pictures of yourself with a sad face that nobody likes or comments on, you are probably depressed. They used the color of the photographs, number of people in the photos, level of engagement, and happiness rated by Mechanical Turk to determine depression.
Wait so they didn't actually go back and see if the people they identified as depressed had a diagnosis of clinical depression?
Earlier quoted context omitted.
Wait so they didn't actually go back and see if the people they identified as depressed had a diagnosis of clinical depression?
What, you thought this was an actual scientific study?
"Data collection was crowdsourced using Amazon’s Mechanical Turk (MTurk) crowdwork platform. Separate surveys were created for depressed and healthy individuals. In the depressed survey, participants were invited to complete a survey that involved passing a series of inclusion criteria, responding to a standardized clinical depression survey, answering questions related to demographics and history of depression, and sharing social media history. We used the CES-D (Center for Epidemiologic Studies Depression Scale) questionnaire to screen participant depression levels [26]. CES-D assessment quality has been demonstrated as on-par with other depression inventories, including the Beck Depression Inventory and the Kellner Symptom Questionnaire [27, 28]. Healthy participants were screened to ensure no history of depression and active Instagram use. See Additional file 1 for actual survey text."
So it sounds like they found depressed and healthy subjects via MTurk and verified them using surveys. I guess that's slightly more rigorous than just "people on MTurk thought the person in this photo looks depressed"