City of the People, for the People: Sensing Urban Dynamics via Social Media Interactions

TL;DR

This paper explores using social media data to analyze urban dynamics, offering a cost-effective alternative to traditional survey and mobile data methods for understanding city activity patterns.

Contribution

It introduces a novel approach to capture urban dynamics through social media activity time series and cluster analysis, demonstrated on London and Doha.

Findings

Effective identification of city and neighborhood activity patterns

Successful clustering of dynamic urban regions

Cost-effective alternative to traditional data sources

Abstract

Understanding the spatio-temporal dynamics of cities is in the heart of many applications including urban planning, zoning, and real-estate construction. So far, much of our understanding about urban dynamics came from traditional surveys conducted by persons or by leveraging mobile data in the form of Call Detailed Records. However, the high financial and human cost associated with these methods make the data availability very limited. In this paper, we investigate the use of large scale and publicly available user contributed content, in the form of social media posts to understand the urban dynamics of cities. We build activity time series for different cities, and different neighborhoods within the same city to identify the different dynamic patterns taking place. Next, we conduct a cluster analysis on the time series to understand the spatial distribution of patterns in the city. Our instantiation for the two cities of London and Doha shows the effectiveness of our method.