There is a strong evidence of spatial patterns in social structures. Distance decay in spatial
interaction processes is a well-known phenomenon, and many recent studies on mobile phone
data sets have conrmed distance decay relationships: the likelihood that two individuals are
connected decreases with distance between them [30]. Generally, social structures of communities
detected from phone data analysis show strong spatial regularity in regional [20] and city
scale levels [45], revealing ner patterns concerned with cultural and socio-economic heterogeneity
of cities. More work is required to extend these ndings to reveal temporal dynamics as
the potential for optimising urban transportation systems through exploiting social structure is
enormous. Spatial interaction also manifests itself in strong spatial consistency in the function
of the city, both dened by infrastructure and underlying urban planning, so as in terms of the
ways people tend to use cities [38] and the temporal evolution of these patterns. The eigenplaces
approach does not ascribe any semantics to these regimes but it is possible to provide
an interpretation by examining changes over space and time, taking into account land use and
services distribution in the city. The analysis of content-rich data from micro-blogging adds
novel dimensions to these studies. Content analysis allows semantically-rich analysis of land
use [41], temporal variability of current-moment interests within cities and related travel behaviours
[37], and inter-city comparisons which reveal common dependencies in human mobility
across countries and continents [34]. Notwithstanding these developments, integrating diverse
real time data from dierent sources is problematic not only from a computational perspective
but also in terms of building integrated models.