Diversity in Online Advertising: A Case Study of 69 Brands on Social Media

Lack of diversity in advertising is a long-standing problem. Despite growing cultural awareness and missed business opportunities, many minorities remain under- or inappropriately represented in advertising. Previous research has studied how people react to culturally embedded ads, but such work focused mostly on print media or television using lab experiments. In this work, we look at diversity in content posted by 69 U.S. brands on two social media platforms, Instagram and Facebook. Using face detection technology, we infer the gender, race, and age of both the faces in the ads and of the users engaging with ads. Using this dataset, we investigate the following: (1) What type of content brands put out – Is there a lack of diversity?; (2) How does a brand’s content diversity compare to its audience diversity – Is any lack of diversity simply a reflection of the audience?; and (3) How does brand diversity relate to user engagement – Do users of a particular demographic engage more if their demographics are represented in a post?

[1]  David R Williams,et al.  The concept and measurement of race and their relationship to public health: a review focused on Brazil and the United States. , 2004, Cadernos de saude publica.

[2]  Christopher Y. Olivola,et al.  Elected in 100 milliseconds: Appearance-Based Trait Inferences and Voting , 2010 .

[3]  Júlio Cesar dos Reis,et al.  Demographics of News Sharing in the U.S. Twittersphere , 2017, HT.

[4]  Paul J. Solomon,et al.  White Consumer Sales Response to Black Models , 1974 .

[5]  Jaakko Lehtinen,et al.  Progressive Growing of GANs for Improved Quality, Stability, and Variation , 2017, ICLR.

[6]  Osei Appiah,et al.  Black, White, Hispanic, and Asian American Adolescents' Responses to Culturally Embedded Ads , 2001 .

[7]  Antonio Torralba,et al.  Using Computer Vision to Study the Effects of BMI on Online Popularity and Weight-Based Homophily , 2018, SocInfo.

[8]  Eric Gilbert,et al.  Faces engage us: photos with faces attract more likes and comments on Instagram , 2014, CHI.

[9]  Hal E. Hershfield,et al.  Increasing Saving Behavior Through Age-Progressed Renderings of the Future Self , 2011, JMR, Journal of marketing research.

[10]  C. Spearman.  The proof and measurement of association between two things. By C. Spearman, 1904. , 1987, The American journal of psychology.

[11]  Brett A. S. Martin,et al.  THE INFLUENCE OF AD MODEL ETHNICITY AND SELF-REFERENCING ON ATTITUDES : Evidence from New Zealand , 2004 .

[12]  Gerald J. Baldasty,et al.  Race, Advertising, and Prime-Time Television , 2003 .

[13]  Venkata Rama Kiran Garimella,et al.  Inferring international and internal migration patterns from Twitter data , 2014, WWW.

[14]  Sora Kim,et al.  How do racial minority consumers process a model race cue in CSR advertising? A comparison of Asian and White Americans , 2019 .

[15]  William J. Qualls,et al.  Stereotyping effects on consumers' evaluation of advertising: Impact of racial differences between actors and viewers , 1990 .

[16]  Hye-Jin Paek,et al.  Racial Ideology, Model Minorities, and the "Not-So-Silent Partner:" Stereotyping of Asian Americans in U.S. Magazine Advertising , 2003, Howard Journal of Communication.

[17]  R. Deshpandé,et al.  Identity salience and the influence of differential activation of the social self-schema on advertising response. , 2002, The Journal of applied psychology.

[18]  Wan-Hsiu Sunny Tsai,et al.  Assimilating the Queers: Representations of Lesbians, Gay Men, Bisexual, and Transgender People in Mainstream Advertising , 2010 .

[19]  David García,et al.  Gender Asymmetries in Reality and Fiction: The Bechdel Test of Social Media , 2014, ICWSM.

[20]  Soon-Gyo Jung,et al.  Assessing the Accuracy of Four Popular Face Recognition Tools for Inferring Gender, Age, and Race , 2018, ICWSM.

[21]  Antonio Torralba,et al.  Face-to-BMI: Using Computer Vision to Infer Body Mass Index on Social Media , 2017, ICWSM.

[22]  A. Miller,et al.  Kenyan patients' attitudes regarding doctor ethnicity and doctor-patient ethnic discordance. , 2011, Patient education and counseling.

[23]  Dirk Schadendorf,et al.  Photoaging Mobile Apps as a Novel Opportunity for Melanoma Prevention: Pilot Study , 2017, JMIR mHealth and uHealth.

[24]  Jisun An,et al.  #greysanatomy vs. #yankees: Demographics and Hashtag Use on Twitter , 2016, ICWSM.

[25]  Michael R. Hyman,et al.  Using a Model's Apparent Ethnicity to Influence Viewer Responses to Print Ads: A Social Identity Theory Perspective , 2009 .