Digital Phenotyping of Big Five Personality via Facebook Data Mining: A Meta-Analysis

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Jun 8, 2020
Davide Marengo Christian Montag

Abstract

Background: 2.7 billion people around the world currently use a product from Facebook such as Instagram, WhatsApp or Facebook itself. These online platforms belong to the most important social media/messenger applications in the world, in particular with a Western view on this topic. Objectives: A growing movement in the scientific community aims to predict psychological traits and states via the study of digital footprints left on these platforms. In particular several researchers demonstrated already that it is feasible to predict personality from posted text on Facebook, but also from a person’s “Like” behavior and so forth. Methods: In the present work we carried out a meta-analysis on the available literature predicting personality from Facebook. Results: Results showed that on average, the accuracy of prediction of user personality scores by mining Facebook data is moderate (r = .33). Discussions: Currently, personality-predictions from social media and smartphone data are feasible, but far away from perfect. Therefore, current predictions from this data cannot be made on individual level. In the near future though, with both more data sets available and more elaborate analysis strategies from artificial intelligence to be applied, this might change.

How to Cite

Marengo, D., & Montag, C. (2020). Digital Phenotyping of Big Five Personality via Facebook Data Mining: A Meta-Analysis. Digital Psychology, 1(1), 52-64. https://doi.org/10.24989/dp.v1i1.1823

Downloads

Download data is not yet available.
Abstract 137 | PDF Downloads 78 R-Codes Downloads 0

##plugins.themes.bootstrap3.article.details##

Keywords

social media, personality, Facebook, digital phenotyping, psychoinformatics

Section
Review article