Name
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. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1145/2424321.2424395 | SIGSPATIAL/GIS |
Keywords | Field | DocType |
urban topic analysis,implicit textual,movement data,urban topic,urban dynamic,implementation architecture,digital trace,incoming data,combined use,event-based citizen-generated data,exploratory visualisations | Modalities,Data mining,Architecture,Computer science,Robustness (computer science),Artificial intelligence,Probabilistic logic,Topic model,Topic analysis,Machine learning | Conference |
Citations | PageRank | References |
42 | 1.38 | 17 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Felix Kling | 1 | 59 | 3.29 |
| Alexei Pozdnoukhov | 2 | 216 | 18.87 |