Marian-Andrei Rizoiu (UTS)

Social media-predicted personality traits and values can help match people to their ideal jobs

Abstract

Scientists are much more open but less agreeable than people in other professions. On the plus side, they’re more likely to be intellectually curious, idealistic, and passionate than non-scientists. But as a group, they also tend to be more rigid, cynical, and tactless. This psychological assessment owes nothing to surveys or personality testing; it pays no heed to the zodiac. Instead, we took the linguistic data from 200 tweets each of nearly 130,000 Twitter users across more than 3,500 occupations to assess their “personality digital fingerprints”. We used machine learning to identify the traits and values that distinguish professions from each other. In doing so we built a “21st century approach for matching one’s personality with congruent occupations,” dubbed the robot career adviser. In this talk, I will show how we collected the data, how we built the system, the resulted Vocation Map and some of the surprising results that emerged. This work was published in the Proceedings of the National Academy of Sciences, in our paper entitled “Social media-predicted personality traits and values can help match people to their ideal jobs”. This work has suscited significant media interest, including BBC, BusinessInsider, Bloomberg and NatureIndex.

Bio

Dr. Marian-Andrei Rizoiu is lecturer with the University of Technology Sydney, leading the Behavioral Data Science group, studying the dynamics of human attention in the online environment. His research has made several key contributions, particularly to the areas of online popularity prediction and online privacy. For the past four years, he has been developing theoretical models for online information diffusion, which can account for complex social phenomena, such as the rise and fall of online popularity, the spread of misinformation or the adoption of disruptive technologies. He approached questions such as “Why did X become popular, but not Y?” and “How can items be promoted?” with implications in advertising and marketing. Marian-Andrei has also worked on detecting the evolution of privacy loss over time. His research has shown that privacy “leaks” over time and it identified the factors causing the loss: the individual’s own actions and the environment. The conclusions were staggering: privacy continues to decrease even for users who retired from activity. Marian-Andrei published in the most selective venues of the field (such as PNAS, WWW, WSDM, ICWSM or CIKM) and his work has received significant media attention, including from the Wikimedia Foundation for the work concerning the privacy of Wikipedia editors (which featured in the March 2016 Wikimedia Research Showcase). See more at http://www.rizoiu.eu