Gokul Chittaranjan and his team, including members from Nokia, published an interesting work which introduces the investigation of the relationship between behavioral characteristics derived from rich smartphone data and self-reported personality traits. They used data stems from smartphones of a set of 83 individuals collected over a continuous period of 8 months. The analysis showed that aggregated features obtained from smartphone usage data can be indicators of the Big-Five personality traits. They also developed an automatic method to infer the personality type of a user based on cellphone usage using supervised learning. Surprisingly, their method performs signicantly above chance and up to 75.9% accuracy.
This seems to be one of the first studies that analysis and classifies the personality characteristics by using smartphone data!
And they won the Pervasive2011 conference best paper award, congratulation guys!