Gridded growing entourage plot of stylistic clusters of images posted to Instagram from five global cities. See zoom detail in image below.
Global Photo Cultures
Billions of photos shared online today are created by people with
different socio-economic characteristics living in different locations.
We introduce a number of methods for quantifying the differences
between such “photo cultures” and apply them to a large collection
of Instagram images shared in five mega-cities around the world.
First, we extract image content and style features and use them
to design a new visualization technique for qualitative analysis of
photo cultures. We then use supervised learning to automatically
recognize and compare visual activity at different locations and expose
surprising connections between geographically distant photo
cultures. Finally, we perform a low-level quantitative analysis to
understand what makes photo cultures different from each other.
Zoom detail of image above. Colored dots in the upper-right corners of the images indicate the city of origin. Green dots, which represent Bangkok—the most stylistically unique city in our data—are conspicuously absent in the center of the cluster. Images closest to the center are stylistically closest to the centroid and thus are most representative of the cluster. Images from Bangkok tend to live in the outer reaches of any multi-city clusters.