Big data is increasingly seen as a way of providing a more ‘scientific’ approach to the understanding and management of cities. But most geographic analyses of geotagged social media data have failed to mobilize a sufficiently complex understanding of socio-spatial relations. By combining the conceptual approach of relational socio-spatial theory with the methods of critical GIScience, this paper explores the spatial imaginaries and processes of segregation and mobility at play in the notion of the ‘9th Street Divide’ in Louisville, Kentucky. Through a more context-sensitive analysis of this data, this paper argues against this popular spatial imaginary and the notion that the Louisville’s West End is somehow separate and apart from the rest of the city. By analyzing the everyday activity spaces of different groups of Louisvillians through geotagged Twitter data, we instead argue for an understanding of these neighborhoods as fluid, porous and actively produced, rather than as rigid, static or fixed. Ultimately, this paper is meant to provide a conceptual and methodological framework for the analysis of social media data that is more attentive to the multiplicity of socio-spatial relations embodied in such data.