• You are currently viewing our forum as a guest, which gives you limited access to view most discussions and access our other features. By joining our free community, you will have access to additional post topics, communicate privately with other members (PM), view blogs, respond to polls, upload content, and access many other special features. Registration is fast, simple and absolutely free, so please join our community today! Just click here to register. You should turn your Ad Blocker off for this site or certain features may not work properly. If you have any problems with the registration process or your account login, please contact us by clicking here.

Using a machine learning algorithm to predict type

Joined
Mar 2, 2016
Messages
625
We'd have to take pictures and feed them into a convolutional neural network to see if it could identify factors that correlate with mbti/socionics/enneagram type. Might make the practice of Visual Identification more rigorous and scientific. Unfortunately you would need a lot of training data. Likely several hundred thousand to several million profile pictures. Maybe you could use Facebook to do it with Cambridge's apply magic sauce framework to guess people's types.

Apply Magic Sauce - Prediction API -

What do you guys think?
 

Spectre

New member
Joined
Nov 22, 2017
Messages
104
MBTI Type
INTJ
Enneagram
5w4
I just peeked at the link.
Intriguing stuff, I must say.
I take it you studied computer science?
 

Julius_Van_Der_Beak

Up the Wolves
Joined
Jul 24, 2008
Messages
19,444
MBTI Type
INTP
Enneagram
5w6
Instinctual Variant
sp/so
I actually know a little about this. I think VI is bogus, though; it's just phrenology for the 21st century.
 

Ghost of the dead horse

filling some space
Joined
Sep 7, 2007
Messages
3,553
MBTI Type
ENTJ
Description of INTP had a Forer-eligible vague statement. My texts were classified as INTP, 50% leadership, "epitome of masculinity" with 0% femininity. I tested 2 texts; I suspect short text length is to blame. They were pretty INTP:ish texts though.

This kind of machine learning seems of somewhat limited value. I don't believe it takes into account the effect of the subject matter - or is it going to classify all computer science articles as NT?
 
Top