An Empirical Study of Geographic User Activity Patterns in Foursquare

By Anastasios Noulas, Salvatore Scellato, Cecilia Mascolo, Massimiliano Pontil. International Conference on Web and Social Media, 2011

555 citations recorded by the source corpus.

We present a large-scale study of user behavior in Foursquare, conducted on a dataset of about 700 thousand users that spans a period of more than 100 days. We analyze user checkin dynamics, demonstrating how it reveals meaningful spatio-temporal patterns and offers the opportunity to study both user mobility and urban spaces. Our aim is to inform on how scientific researchers could utilise data generated in Location-based Social Networks to attain a deeper understanding of human mobility and how developers may take advantage of such systems to enhance applications such as recommender systems.

Subfields: Computer Science Applications, Statistical and Nonlinear Physics, Transportation

View Paper: https://www.semanticscholar.org/paper/fd59f25da4eac25875c9f2f431970077e12a7d9c

How researchers see this paper

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

In Computer Science Applications

In Statistical and Nonlinear Physics

In Transportation

Citations in the corpus

Combining Social Media and Survey Data to Nowcast Migrant Stocks in the United States (2020, background): “The earliest papers illustrated how geo-located data from email services and web-based applications such as Twitter, Google Latitude, Foursquare or Yahoo! can be used (Ferrari et al., 2011; Noulas et al., 2011; Zagheni and Weber, 2012).”
Regions, Periods, Activities: Uncovering Urban Dynamics via Cross-Modal Representation Learning (2017, background): “[27] analyze user activities with massive Foursquare checkins and find the checkin data can reveal meaningful spatiotemporal activity patterns; Cho et al.”
Inferring international and internal migration patterns from Twitter data (2014, methodology): “Localized mobility, often within a city, has been measured using data from Twitter [12], Google Latitude [11], Foursquare [17] and public transport fare collection sensors [15, 22].”
Mining point-of-interest data from social networks for urban land use classification and disaggregation (2015, methodology): “For example, using a large commercial POI database, Santos and Moreira (2006) create and classify location contexts using decision trees, identifying clusters via a density-based clustering algorithm to define areas (or regions) through the application of a concave hull algorithm and classify a give”
Content-Aware Point of Interest Recommendation on Location-Based Social Networks (2015, background): “Due to the strong correlations between geographical distance and social connections discovered in previous work (Cheng et al. 2011; Cho, Myers, and Leskovec 2011; Scellato et al. 2011; Noulas et al. 2011; Zhang et al. 2012; Gao, Tang, and Liu 2012; Long and Joshi 2013; Chang and Sun 2011), current w”
Event-based social networks: linking the online and offline social worlds (2012, background): “Although adjacent location checkins may indicate implicit social interactions and social ties [5], checkins are usually sporadic [21] and largely represent individual behaviors.”
Recommendations in location-based social networks: a survey (2015, background): “Foursquare 1 [73] Foursquare5 is a location-based social networking website, where the users can check-in/comment at the nearby venues.”
On the validity of geosocial mobility traces (2013, methodology): “Our main dataset came from ordinary Foursquare users who installed our application from Google Play and Amazon App stores.”
Locative media and data-driven computing experiments (2016, methodology): “To this end, attempts have been made to measure the importance of social and spatial ‘structures’ in locative media and determine appropriate models for predicting urban social interactions, which can be exemplified in the work by Scellato et al .”
NationTelescope: Monitoring and visualizing large-scale collective behavior in LBSNs (2015, methodology): “[13] conducted an empirical study of geographic user activity patterns based on check-in data in Foursquare.”
Representation and communication: challenges in interpreting large social media datasets (2013, methodology): “[22] presented an analysis of the geo-temporal dynamics by analysing tweets that contain check-ins and Cheng et al.”
Fused Matrix Factorization with Geographical and Social Influence in Location-Based Social Networks (2012, background): “Contrarily, LBSNs data are in large-scale, but very sparse (Noulas et al. 2011; Scellato et al. 2011).”
Time-aware point-of-interest recommendation (2013, background): “Temporal behavior: Temporal influence plays an important role in analyzing users’ daily activities [16].”
Where You Like to Go Next: Successive Point-of-Interest Recommendation (2013, unknown): “We obtain similar results in [Noulas et al. , 2011] and observe two signiﬁcant properties on the LBSN data: personalized Markov chain and localized region constraint.”
Rank-GeoFM: A Ranking based Geographical Factorization Method for Point of Interest Recommendation (2015, background): “For example, geographical coordinates, as an important type of context information which is not available in conventional recommendation tasks, are exploited for POI recommendation [22, 15, 3], since users have a much higher probability to visit nearby POIs [22, 15].”
Demographic research with non-representative internet data (2015, methodology): “An Empirical Study of Geographic User Activity Patterns in Foursquare.”
Beyond "local", "categories" and "friends": clustering foursquare users with latent "topics" (2012, background): “Data drawn from mobile devices on the whereabouts of their users has led to an influx of interesting findings in explaining patterns of human mobility [6, 17, 5], predicting friendship on social networking sites based on location data [23, 20], and better understanding different aspects of cities, b”
"Will Check-in for Badges": Understanding Bias and Misbehavior on Location-Based Social Networks (2021, background): “…researchers have relied on mobility models (Johnson and Maltz 1996; Jardosh et al. 2003), geotagged data via IP addresses ( e.g. , Wikipedia), or user check-in data available via APIs ( e.g. , Foursquare) (Cheng et al. 2011; Noulas and others 2011; Sen and others 2015; Hecht and Stephens 2014).”
Exploring temporal effects for location recommendation on location-based social networks (2013, background): “The large-scale check-in data on LBSNs is usually very sparse due to the user-driven check-in property [19, 17, 8].”