NeuralType

Inspiration

InMind 2 game, neuroscience and Socionics (like Myers–Briggs Type Indicator).

What it does

Predicting personality type by neural network analysis.

How I built it

I built it with:

Science research we did previously while develop InMind & InMind 2 games
Dataset collect for InMind 2
TensorFlow models (public & own developed)
A well-accepted theory of psychology, marketing, and other fields is that human language reflects personality, thinking style, social connections, and emotional states.

The frequency with which we use certain categories of words can provide clues to these characteristics. Several researchers found that variations in word usage in writings such as blogs, essays, and tweets can predict aspects of personality (Fast & Funder, 2008; Gill et al., 2009; Golbeck et al., 2011; Hirsh & Peterson, 2009; and Yarkoni, 2010).

Result example - targeting the top 10 percent of users in terms of high openness and low emotional range resulted in increases in click rate from 6.8 percent to 11.3 percent and in follow rate from 4.7 percent to 8.8 percent.

Challenges I ran into

It's not challenge, it's like science hypothesis testing :) So i have the hypothesis that it's possible for complex neural model to find positive correlation between human's personality type and text style/appearance. To check application of this i'll run prediction on database of my friends's startup about learning english (couples Teacher-Student) and look at correlation between personality types matching and length of staying with one teacher (it's possible to request another teacher if you want anytime).