Studying the Live Cross-Platform Circulation of Images With Computer Vision API: An Experiment Based on a Sports Media Event

Carlos d'Andrea, André Mintz


This article proposes a novel digital methods approach for studying the cross-platform circulation of images, taking these as traffic tags connecting topics across platforms and the open Web. To that end, it makes use of a computer vision API (Google Cloud Vision) to perform automated content-based image searches. The method is experimented on with an analysis of the circulation of pictures shared on Twitter during the 2018 FIFA World Cup Final Draw ceremony. The proposed approach showed high potential for overcoming linguistic and geographical barriers in Internet research by its use of nonverbal objects for cross-linking online content. Moreover, the analysis of the results raised important questions about the opacity of the employed API mechanisms and the limitations imposed by platformization processes for cross-platform endeavors, calling for continued reflexivity in derived studies.


digital methods, cross-platform, computer vision, media event

Full Text: