When a city tells a story

Abstract

This paper explores the use of textual and event-based citizen-generated data from services such as Twitter and Foursquare to study urban dynamics. It applies a probabilistic topic model to obtain a decomposition of the stream of digital traces into a set of urban topics related to various activities of the citizens in the course of a week. Due to the combined use of implicit textual and movement data, we obtain semantically rich modalities of the urban dynamics and overcome the drawbacks of several previous attempts. Other important advantages of our method include its flexibility and robustness with respect to the varying quality and volume of the incoming data. We describe an implementation architecture of the system, the main outputs of the analysis, and the derived exploratory visualisations. Finally, we discuss the implications of our methodology for enriching location-based services with real-time context.

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 — 107 citations exist upstream.

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