Graffiti on freight trains exists in a constant duality between the physical and digital realms, manifesting as works of art that circulate across the North American continent and are documented on user-generated content platforms. This phenomenon reflects the growing 'datafication' of everyday life and is explored through various theoretical perspectives and techniques. Computational social sciences offer a valuable conceptual framework for analyzing this phenomenon. Instead of making up new concepts, researchers adapt existing frameworks to interpret data using computational tools and artificial intelligence, which allow for the aggregation and analysis of large volumes of data and the discovery of hidden patterns interpreted on solid conceptual frameworks. However, analyzing New York graffiti on freight trains requires specialized and niche approaches, involving data collection, custom model training, and the use of unconventional metrics.This paper shares the author's experience as a researcher, showing how the perspective of computational social sciences guided an investigation into a type of graffiti and a geographically dispersed community. It discusses the theoretical and methodological decisions made, as well as the limits, scope, and possibilities of this approach.
Read the paper