University of Cambridge > Talks.cam > Social Psychology Seminar Series (SPSS) > A zero-item personality test? Predicting personality traits from social media data

A zero-item personality test? Predicting personality traits from social media data

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Elisa Militaru.

Many researchers, including myself (e.g. Kosinski, Graepel & Stillwell, 2013), have published papers showing that psychological traits like personality and intelligence can be predicted from the digital footprints people leave behind when they use online services like social media. But are these predictions psychometrically reliable, valid, and unbiased? The Facebook Cambridge Analytica scandal clearly demonstrates that the public is uneasy when they feel their data was misused, but on the other hand the public also likes their data to be used to personalise recommendations and services. Ultimately, should this technology be used in practice, and if so under what conditions?

Dr. David Stillwell is Lecturer in Big Data Analytics and Quantitative Social Science at Judge Business School in the University of Cambridge. He is also Academic Director of the Psychometrics Centre. David studies the links between big data and psychology; his research with 6 million social media users found that the computer can predict a user’s personality as accurately as their spouse can. Follow up research found that personalizing an advert to the recipient’s psychology is more effective than generic ads. David has also published research using various big data sources to show that spending money on products and services that match one’s personality leads to greater life satisfaction, that people tend to date others who have a similar personality, and that people who swear seem to be more honest.

Twitter: @david_stillwell

This talk is part of the Social Psychology Seminar Series (SPSS) series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2020 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity