Zoning of St. Petersburg Through the Prism of Social Activity Networks

Abstract

Cities are complex systems and understanding their structure is critical for multiple applications. However, traditional urban planning is challenged by the dynamics of the urban system. Fortunately, in recent years, multiple datasets reflecting human activity in nearly real-time have become available. This paper leverages geo-tagged VKontakte and Google Places social media data for building three different networks between locations across Saint-Petersburg and revealing the structure of the city through the community structure of those networks. Comparative analysis of the discovered network structure and its ability to capture meaningful socio-economic patterns across the city is evaluated. Results will aid urban, transportation, infrastructural planning, policy-making, real estate and socio-economic development initiatives.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 5 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.