The Face of Persuasion: Analyzing Bias and Generating Culture-Aware Ads
This addresses bias and customization in AI-generated advertising, but it is incremental as it builds on existing text-to-image models.
The study examined demographic bias and persuasiveness in text-to-image generated ads, finding disparities based on gender and race, and tested a technique for targeting ads by country.
Text-to-image models are appealing for customizing visual advertisements and targeting specific populations. We investigate this potential by examining the demographic bias within ads for different ad topics, and the disparate level of persuasiveness (judged by models) of ads that are identical except for gender/race of the people portrayed. We also experiment with a technique to target ads for specific countries. The code is available at https://github.com/aysanaghazadeh/FaceOfPersuasion