The Livehoods Project: Utilizing Social Media to Understand the Dynamics of a City

By Justin Cranshaw, Raz Schwartz, Jason I. Hong, Norman M. Sadeh. 2012

677 citations recorded by the source corpus.

Studying the social dynamics of a city on a large scale has tra- ditionally been a challenging endeavor, requiring long hours of observation and interviews, usually resulting in only a par- tial depiction of reality. At the same time, the boundaries of municipal organizational units, such as neighborhoods and districts, are largely statically defined by the city government and do not always reflect the character of life in these ar- eas. To address both difficulties, we introduce a clustering model and research methodology for studying the structure and composition of a city based on the social media its res- idents generate. We use data from approximately 18 million check-ins collected from users of a location-based online so- cial network. The resulting clusters, which we call Livehoods, are representations of the dynamic urban areas that comprise the city. We take an interdisciplinary approach to validating these clusters, interviewing 27 residents of Pittsburgh, PA, to see how their perceptions of the city project onto our findings there. Our results provide strong support for the discovered clusters, showing how Livehoods reveal the distinctly charac- terized areas of the city and the forces that shape them.

Subfields: Building and Construction, Geography, Planning and Development, Transportation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Building and Construction

In Geography, Planning and Development

In Transportation

Citations in the corpus

Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries (2019, background): “…quantiﬁed (Charmaz, 2014); can be used for in-depth explorations of quantitative measurements to validate or discern the nuances of their social meanings (Cranshaw et al., 2012; Tufekci, 2014); or can involve the development of codebooks to quantitatively code larger corpora (Vieweg et al., 2010).”
A Tale of Cities: Urban Biases in Volunteered Geographic Information (2014, methodology): “Finally, our work also suggests that VGI-based methods that have been demonstrated to be highly effective in urban areas (e.g. Cranshaw et al. 2012) may have to be significantly altered in order to be effective in rural areas, especially methods relying on Foursquare data.”
The Geography and Importance of Localness in Geotagged Social Media (2016, background): “For instance, this has occurred in work that seeks to describe diurnal patterns in sentiment [15], predict public health measures [9], and measure human mobility [5], among other studies (e.g., [1,8,50]).”
The Emerging Internet of Things Marketplace From an Industrial Perspective: A Survey (2015, background): “Activity Monitoring Livehoods [83] offers a new way to conceptualise the dynamics, structure, and character of a city by analysing the social media its residents generate.”
Towards Decision Support and Goal Achievement: Identifying Action-Outcome Relationships From Social Media (2015, positive): “Similar studies have been conducted in urban informatics [8], mental health [9, 16], natural disaster monitoring [11, 41], and other domains.”
NationTelescope: Monitoring and visualizing large-scale collective behavior in LBSNs (2015, background): “[14] studied the dynamics of a city based on user collective behavior in LBSNs.”
Participatory Cultural Mapping Based on Collective Behavior Data in Location-Based Social Networks (2016, methodology): “to Cranshaw et al. [2012], we also integrate a method to auto-select the number of clusters within a given range. Algorithm 3 presents the clustering process. Let M denote an affinity matrix of cities with the size of nc ∗ nc, where nc is the number of cities. We also define a range for the number o”
Discovering Urban Functional Zones Using Latent Activity Trajectories (2015, background): “graphic distribution of some topic in terms of user-generated social media [33], [34].”
Representation and communication: challenges in interpreting large social media datasets (2013, background): “Location-based social media (from services such as Foursquare and Twitter) have been used to infer details about travel patterns and behaviours [11, 22] and with the increasing possibility of location sensing, large scale location data has be used to predict social events attendance [7] or to infer ”
State of the Geotags: Motivations and Recent Changes (2017, methodology): “LiveHoods (Cranshaw et al. 2012) and HoodSquare (Zhang et al. 2013), for example, used Foursquare checkins to ﬁnd organic boundaries of neighborhoods.”
Mining point-of-interest data from social networks for urban land use classification and disaggregation (2015, background): “…social networks The potential of location-based (LB) social networks (like Gowalla, Foursquare, and Facebook Places) has already been demonstrated in recent studies and is increasingly exploited as the dimensions of such services grow (e.g., Cranshaw, Hong, & Sadeh, 2012; Long, Jin, & Joshi, 2012).”
The Effect of Population and "Structural" Biases on Social Media-based Algorithms: A Case Study in Geolocation Inference Across the Urban-Rural Spectrum (2017, background): “, [1,12,13]), social media has also been a major catalyst in the development of new intelligent algorithms.”
Proactive edge computing in latency-constrained fog networks (2017, methodology): “ces together. The similarity matrix Sis calculated as: S= S d + (1 )S p; (11) where is a parameter that adjusts the impact of distance and task popularity. Subsequently, we use spectral clustering [15] to group UNs into kdisjoint clusters, C 1;:::;C k. To bring the popular tasks closer to the networ”
Exploiting Geographical Neighborhood Characteristics for Location Recommendation (2014, methodology): “3 For illustration purpose, here we present a clustering result by using user check-in similarity with geographical constraint, similar to that re-ported in [4].”
Extracting Diurnal Patterns of Real World Activity from Social Media (2013, background): “2011) and activity on Foursquare to model city dynamic structure and functional use (Cranshaw et al. 2012; Kling and Pozdnoukhov 2012).”
Beyond "local", "categories" and "friends": clustering foursquare users with latent "topics" (2012, methodology): “, in [7], present an approach which utilizes geographic proximity in combination with user check in history, thus incorporating a better understanding of the specific places people travel to.”
Uncovering Patterns of Inter-Urban Trip and Spatial Interaction from Social Media Check-In Data (2013, background): “At the aggregate level, these data enables us to study spatial activity distributions and spatial interactions between regions [6].”