TY - JOUR
T1 - Predicting individual-level income from Facebook profiles
AU - Matz, Sandra C.
AU - Menges, Jochen I.
AU - Stillwell, David J.
AU - Schwartz, H. Andrew
N1 - Publisher Copyright:
© 2019 Matz et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
PY - 2019/3
Y1 - 2019/3
N2 - Information about a person’s income can be useful in several business-related contexts, such as personalized advertising or salary negotiations. However, many people consider this information private and are reluctant to share it. In this paper, we show that income is predictable from the digital footprints people leave on Facebook. Applying an established machine learning method to an income-representative sample of 2,623 U.S. Americans, we found that (i) Facebook Likes and Status Updates alone predicted a person’s income with an accuracy of up to r = 0.43, and (ii) Facebook Likes and Status Updates added incremental predictive power above and beyond a range of socio-demographic variables (ΔR2 = 6–16%, with a correlation of up to r = 0.49). Our findings highlight both opportunities for businesses and legitimate privacy concerns that such prediction models pose to individuals and society when applied without individual consent.
AB - Information about a person’s income can be useful in several business-related contexts, such as personalized advertising or salary negotiations. However, many people consider this information private and are reluctant to share it. In this paper, we show that income is predictable from the digital footprints people leave on Facebook. Applying an established machine learning method to an income-representative sample of 2,623 U.S. Americans, we found that (i) Facebook Likes and Status Updates alone predicted a person’s income with an accuracy of up to r = 0.43, and (ii) Facebook Likes and Status Updates added incremental predictive power above and beyond a range of socio-demographic variables (ΔR2 = 6–16%, with a correlation of up to r = 0.49). Our findings highlight both opportunities for businesses and legitimate privacy concerns that such prediction models pose to individuals and society when applied without individual consent.
UR - https://www.scopus.com/pages/publications/85063640239
U2 - 10.1371/journal.pone.0214369
DO - 10.1371/journal.pone.0214369
M3 - Article
C2 - 30921389
AN - SCOPUS:85063640239
SN - 1932-6203
VL - 14
JO - PLoS ONE
JF - PLoS ONE
IS - 3
M1 - e0214369
ER -