Assessing the Reliability of Facebook’s Advertising Data for Use in Demographic Research
Andre Grow1, Daniela Perrotta, Emanuele Del Fava1, Jorge Cimentada1, Francesco Rampazzo2, Sofia Gil-Clavel1, Emilio Zagheni1, René Flores3, Ilana Ventura3, Ingmar Weber4, Kiran Garimella
1Max Planck Institute for Demographic Research, 2University of Oxford, 3University of Chicago, 4Qatar Computing Research Institute, HBKU

An increasing number of scholars advocate the use of Facebook’s advertising platform in demographic research, either for conducting digital censuses that provide information about the composition of the population at large, or for recruiting participants for survey research. The efficacy of both approaches depends on the accuracy of the data that Facebook provides about its users, but little is known about how reliable these data are. We address this gap by comparing individuals’ self-reported information in a large-scale, cross-national online survey (N = 93,109) with the way Facebook classified same individuals. We focus on participants’ sex, age, and region of residence, which are common stratification variables in demographic research. We find that the reliability of the classification varies across characteristics, with sex being most reliable and region being least reliable. Our results suggest that Facebook’s advertising platform can be fruitfully used in demographic research, with some caveats.