Using Facebook Ads audiences for global lifestyle disease surveillance

Promises and limitations

Matheus Araújo, Yelena Mejova, Ingmar Weber, Fabrício Benevenuto

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

Abstract

Every day, millions of users reveal their interests on Facebook, which are then monetized via targeted advertisement marketing campaigns. In this paper, we explore the use of demographically rich Facebook Ads audience estimates for tracking non-communicable diseases around the world. Across 47 countries, we compute the audiences of marker interests, and evaluate their potential in tracking health conditions associated with tobacco use, obesity, and diabetes, compared to the performance of placebo interests. Despite its huge potential, we find that, for modeling prevalence of health conditions across countries, differences in these interest audiences are only weakly indicative of the corresponding prevalence rates. Within the countries, however, our approach provides interesting insights on trends of health awareness across demographic groups. Finally, we provide a temporal error analysis to expose the potential pitfalls of using Facebook's Marketing API as a black box.

Original languageEnglish
Title of host publicationWebSci 2017 - Proceedings of the 2017 ACM Web Science Conference
PublisherAssociation for Computing Machinery, Inc
Pages253-257
Number of pages5
ISBN (Electronic)9781450348966
DOIs
Publication statusPublished - 25 Jun 2017
Event9th ACM Web Science Conference, WebSci 2017 - Troy, United States
Duration: 25 Jun 201728 Jun 2017

Other

Other9th ACM Web Science Conference, WebSci 2017
CountryUnited States
CityTroy
Period25/6/1728/6/17

Fingerprint

Health
Marketing
Tobacco
Medical problems
Application programming interfaces (API)
Error analysis

Keywords

  • Advertising
  • Epidemiology
  • Facebook
  • Health
  • Social media

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

Araújo, M., Mejova, Y., Weber, I., & Benevenuto, F. (2017). Using Facebook Ads audiences for global lifestyle disease surveillance: Promises and limitations. In WebSci 2017 - Proceedings of the 2017 ACM Web Science Conference (pp. 253-257). Association for Computing Machinery, Inc. https://doi.org/10.1145/3091478.3091513

Using Facebook Ads audiences for global lifestyle disease surveillance : Promises and limitations. / Araújo, Matheus; Mejova, Yelena; Weber, Ingmar; Benevenuto, Fabrício.

WebSci 2017 - Proceedings of the 2017 ACM Web Science Conference. Association for Computing Machinery, Inc, 2017. p. 253-257.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Araújo, M, Mejova, Y, Weber, I & Benevenuto, F 2017, Using Facebook Ads audiences for global lifestyle disease surveillance: Promises and limitations. in WebSci 2017 - Proceedings of the 2017 ACM Web Science Conference. Association for Computing Machinery, Inc, pp. 253-257, 9th ACM Web Science Conference, WebSci 2017, Troy, United States, 25/6/17. https://doi.org/10.1145/3091478.3091513
Araújo M, Mejova Y, Weber I, Benevenuto F. Using Facebook Ads audiences for global lifestyle disease surveillance: Promises and limitations. In WebSci 2017 - Proceedings of the 2017 ACM Web Science Conference. Association for Computing Machinery, Inc. 2017. p. 253-257 https://doi.org/10.1145/3091478.3091513
Araújo, Matheus ; Mejova, Yelena ; Weber, Ingmar ; Benevenuto, Fabrício. / Using Facebook Ads audiences for global lifestyle disease surveillance : Promises and limitations. WebSci 2017 - Proceedings of the 2017 ACM Web Science Conference. Association for Computing Machinery, Inc, 2017. pp. 253-257
@inproceedings{528efea9edc14ee4a2612c66da605f41,
title = "Using Facebook Ads audiences for global lifestyle disease surveillance: Promises and limitations",
abstract = "Every day, millions of users reveal their interests on Facebook, which are then monetized via targeted advertisement marketing campaigns. In this paper, we explore the use of demographically rich Facebook Ads audience estimates for tracking non-communicable diseases around the world. Across 47 countries, we compute the audiences of marker interests, and evaluate their potential in tracking health conditions associated with tobacco use, obesity, and diabetes, compared to the performance of placebo interests. Despite its huge potential, we find that, for modeling prevalence of health conditions across countries, differences in these interest audiences are only weakly indicative of the corresponding prevalence rates. Within the countries, however, our approach provides interesting insights on trends of health awareness across demographic groups. Finally, we provide a temporal error analysis to expose the potential pitfalls of using Facebook's Marketing API as a black box.",
keywords = "Advertising, Epidemiology, Facebook, Health, Social media",
author = "Matheus Ara{\'u}jo and Yelena Mejova and Ingmar Weber and Fabr{\'i}cio Benevenuto",
year = "2017",
month = "6",
day = "25",
doi = "10.1145/3091478.3091513",
language = "English",
pages = "253--257",
booktitle = "WebSci 2017 - Proceedings of the 2017 ACM Web Science Conference",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - Using Facebook Ads audiences for global lifestyle disease surveillance

T2 - Promises and limitations

AU - Araújo, Matheus

AU - Mejova, Yelena

AU - Weber, Ingmar

AU - Benevenuto, Fabrício

PY - 2017/6/25

Y1 - 2017/6/25

N2 - Every day, millions of users reveal their interests on Facebook, which are then monetized via targeted advertisement marketing campaigns. In this paper, we explore the use of demographically rich Facebook Ads audience estimates for tracking non-communicable diseases around the world. Across 47 countries, we compute the audiences of marker interests, and evaluate their potential in tracking health conditions associated with tobacco use, obesity, and diabetes, compared to the performance of placebo interests. Despite its huge potential, we find that, for modeling prevalence of health conditions across countries, differences in these interest audiences are only weakly indicative of the corresponding prevalence rates. Within the countries, however, our approach provides interesting insights on trends of health awareness across demographic groups. Finally, we provide a temporal error analysis to expose the potential pitfalls of using Facebook's Marketing API as a black box.

AB - Every day, millions of users reveal their interests on Facebook, which are then monetized via targeted advertisement marketing campaigns. In this paper, we explore the use of demographically rich Facebook Ads audience estimates for tracking non-communicable diseases around the world. Across 47 countries, we compute the audiences of marker interests, and evaluate their potential in tracking health conditions associated with tobacco use, obesity, and diabetes, compared to the performance of placebo interests. Despite its huge potential, we find that, for modeling prevalence of health conditions across countries, differences in these interest audiences are only weakly indicative of the corresponding prevalence rates. Within the countries, however, our approach provides interesting insights on trends of health awareness across demographic groups. Finally, we provide a temporal error analysis to expose the potential pitfalls of using Facebook's Marketing API as a black box.

KW - Advertising

KW - Epidemiology

KW - Facebook

KW - Health

KW - Social media

UR - http://www.scopus.com/inward/record.url?scp=85026762672&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85026762672&partnerID=8YFLogxK

U2 - 10.1145/3091478.3091513

DO - 10.1145/3091478.3091513

M3 - Conference contribution

SP - 253

EP - 257

BT - WebSci 2017 - Proceedings of the 2017 ACM Web Science Conference

PB - Association for Computing Machinery, Inc

ER -