Insta(nt) Pet Therapy: GAN-generated Images for Therapeutic Social Media Content

Abstract

The positive therapeutic effect of viewing pet images online has been well-studied. However, it is difficult to obtain large-scale production of such content since it relies on pet owners to capture photographs and upload them. I use a Generative Adversarial Network-based framework for the creation of fake pet images at scale. These images are uploaded on an Instagram account where they drive user engagement at levels comparable to those seen with images from accounts with traditional pet photographs, underlining the applicability of the framework to be used for pet-therapy social media content.