Overprofiling Analysis on Major Internet Players
Authors: Francisco Caravaca (Universidad Carlos III de Madrid), José González-Cabañas (UC3M-Santander Big Data Institute), Ángel Cuevas (Universidad Carlos III de Madrid; UC3M-Santander Big Data Institute), Rubén Cuevas (Universidad Carlos III de Madrid; UC3M-Santander Big Data Institute)
Volume: 2024
Issue: 4
Pages: 929–946
DOI: https://doi.org/10.56553/popets-2024-0149
Abstract: Many Internet services obtain their revenue through the delivery of online advertisements based on the commercial exploitation of users’ profiles. The accuracy and size of these profiles have important implications in terms of advertisers’ campaign performance and users’ privacy. Despite the importance of auditing the profiling accuracy, very little effort has been devoted both in industry and academia. This paper presents the most comprehensive auditing effort to understand the profiling accuracy of four major online advertising platforms: Google, Facebook, Twitter, and LinkedIn. Our work unveils that less than 50% of the assigned interests are relevant. Moreover, platforms can distinguish what interests within the assigned ones are more relevant but hide this information from users and advertisers. Finally, we have proposed a very simple solution that only uses 25 general interests per user. This proposal outperforms all the analyzed platforms in terms of profile accuracy while improving users’ privacy.
Keywords: privacy, social networks, advertisement, interests
Copyright in PoPETs articles are held by their authors. This article is published under a Creative Commons Attribution 4.0 license.
