Anastasios Noulas

A tale of many cities: universal patterns in human urban mobility.

The advent of geographic online social networks such as Foursquare, where users voluntarily signal their current location, opens the door to powerful studies on human movement. In particular the fine granularity of the location data, with GPS accuracy down to 10 meters, and the worldwide scale of Foursquare adoption are unprecedented. In this paper we study urban mobility patterns of people in several metropolitan cities around the globe by analyzing a large set of Foursquare users. Surprisingly, while there are variations in human movement in different cities, our analysis shows that those are predominantly due to different distributions of places across different urban environments. Moreover, a universal law for human mobility is identified, which isolates as a key component the rank-distance, factoring in the number of places between origin and destination, rather than pure physical distance, as considered in some previous works. Building on our findings, we also show how a rank-based movement model accurately captures real human movements in different cities.

Geo-spotting: mining online location-based services for optimal retail store placement

The problem of identifying the optimal location for a new retail store has been the focus of past research, especially in the field of land economy, due to its importance in the success of a business. Traditional approaches to the problem have factored in demographics, revenue and aggregated human flow statistics from nearby or remote areas. However, the acquisition of relevant data is usually expensive. With the growth of location-based social networks, fine grained data describing user mobility and popularity of places has recently become attainable. In this paper we study the predictive power of various machine learning features on the popularity of retail stores in the city through the use of a dataset collected from Foursquare in New York. The features we mine are based on two general signals: geographic, where features are formulated according to the types and density of nearby places, and user mobility, which includes transitions between venues or the incoming flow of mobile users from distant areas. Our evaluation suggests that the best performing features are common across the three different commercial chains considered in the analysis, although variations may exist too, as explained by heterogeneities in the way retail facilities attract users. We also show that performance improves significantly when combining multiple features in supervised learning algorithms, suggesting that the retail success of a business may depend on multiple factors.

Exploiting Foursquare and Cellular Data to Infer User Activity in Urban Environments

Inferring the type of activities in neighborhoods of urban centers may be helpful in a number of contexts including urban planning, content delivery and activity recommendations for mobile web users or may even yield to a deeper understanding of the geographical evolution of social life in the city . During the past few years, the analysis of mobile phone usage patterns, or of social media with longitudinal attributes, have aided the automatic characterization of the dynamics of the urban environment. In this work, we combine a dataset sourced from a telecommunication provider in Spain with a database of millions of geotagged venues from Foursquare and we formulate the problem of urban activity inference in a supervised learning framework. In particular, we exploit user communication patterns observed at the base station level in order to predict the activity of Foursquare users who checkin-in at nearby venues. First, we mine a set of machine learning features that allow us to encode the input telecommunication signal of a tower. Subsequently, we evaluate a diverse set of supervised learning algorithms using labels extracted from Foursquare place categories and we consider two application scenarios. Initially, we assess how hard it is to predict specific urban activity of an area, showing that Nightlife and Entertainment spots are those easier to infer, whereas College and Shopping areas are those featuring the lowest accuracy rates. Then, considering a candidate set of activity types in a geographic area, we aim to elect the most prominent one. We demonstrate how the difficulty of the problem increases with the number of classes incorporated in the prediction task, yet the classifiers achieve a considerably better performance compared to a random guess even when the set of candidate classes increases.

#FoodPorn: Obesity Patterns in Culinary Interactions

We present a large-scale analysis of Instagram pictures taken at 164,753 restaurants by millions of users. Motivated by the obesity epidemic in the United States, our aim is three-fold: (i) to assess the relationship between fast food and chain restaurants and obesity, (ii) to better understand peoples thoughts on and perceptions of their daily dining experiences, and (iii) to reveal the nature of social reinforcement and approval in the context of dietary health on social media. When we correlate the prominence of fast food restaurants in US counties with obesity, we find the Foursquare data to show a greater correlation at 0.424 than official survey data from the County Health Rankings would show. Our analysis further reveals a relationship between small businesses and local foods with better dietary health, with such restaurants getting more attention in areas of lower obesity. However, even in such areas, social approval favors the unhealthy foods high in sugar, with donut shops producing the most liked photos. Thus, the dietary landscape our study reveals is a complex ecosystem, with fast food playing a role alongside social interactions and personal perceptions, which often may be at odds.

Hoodsquare: Modeling and Recommending Neighborhoods in Location-Based Social Networks

Information garnered from activity on location-based social networks can be harnessed to characterize urban spaces and organize them into neighborhoods. We represent geographic points in the city using spatio-temporal information about Foursquare user check-ins and semantic information about places, with the goal of developing features to input into a novel neighborhood detection algorithm. The algorithm first employs a similarity metric that assesses the homogeneity of a geographic area, and then with a simple mechanism of geographic navigation, it detects the boundaries of a citys neighborhoods. The models and algorithms devised are subsequently integrated into a publicly available, map-based tool named Hood square that allows users to explore activities and neighborhoods in cities around the world. Finally, we evaluate Hood square in the context of are commendation application where user profiles are matched to urban neighborhoods. By comparing with a number of baselines, we demonstrate how Hood square can be used to accurately predict the home neighborhood of Twitter users. We also show that we are able to suggest neighborhoods geographically constrained in size, a desirable property in mobile recommendation scenarios for which geographical precision is key.

A multilayer approach to multiplexity and link prediction in online geo-social networks

Online social systems are multiplex in nature as multiple links may exist between the same two users across different social media. In this work, we study the geo-social properties of multiplex links, spanning more than one social network and apply their structural and interaction features to the problem of link prediction across social networking services. Exploring the intersection of two popular online platforms - Twitter and location-based social network Foursquare - we represent the two together as a composite multilayer online social network, where each platform represents a layer in the network. We find that pairs of users connected on both services, have greater neighbourhood similarity and are more similar in terms of their social and spatial properties on both platforms in comparison with pairs who are connected on just one of the social networks. Our evaluation, which aims to shed light on the implications of multiplexity for the link generation process, shows that we can successfully predict links across social networking services. In addition, we also show how combining information from multiple heterogeneous networks in a multilayer configuration can provide new insights into user interactions on online social networks, and can significantly improve link prediction systems with valuable applications to social bootstrapping and friend recommendations.

The importance of being placefriends: discovering location-focused online communities

Discovering groups of online friends who go to the same physical places has numerous potential applications including privacy management, friend recommendation, and contact grouping as in Google+ circles. Until recently, little information was available about places visited by users of online social networking services, so community detection on the social graph could not take this into account. With the rise of services such as Foursquare, Gowalla, and Facebook Places, where users check in to named venues and share their location with their friends, we now have the right data to make this possible. In this work, we propose a way to extract place-focused communities from the social graph by annotating its edges with check-in information. Using traces from two online social networks with location sharing, we show that we can extract groups of friends who meet face-to-face, with many possible benefits for online social services.

A Place-Focused Model for Social Networks in Cities

The focused organization theory of social ties proposes that the structure of human social networks can be arranged around extra-network foci, which can include shared physical spaces such as homes, workplaces, restaurants, and so on. Until now, this has been difficult to investigate on a large scale, but the huge volume of data available from online location-based social services now makes it possible to examine the friendships and mobility of many thousands of people, and to investigate the relationship between meetings at places and the structure of the social network. In this paper, we analyze a large dataset from Foursquare, the most popular online location-based social network. We examine the properties of city-based social networks, finding that they have common structural properties, and that the category of place where two people meet has very strong influence on the likelihood of their being friends. Inspired by these observations in combination with the focused organization theory, we then present a model to generate city-level social networks, and show that it produces networks with the structural properties seen in empirical data.

Social and place-focused communities in location-based online social networks

Abstract Thanks to widely available, cheap Internet access and the ubiquity of smartphones, millions of people around the world now use online location-based social networking services. Understanding the structural properties of these systems and their dependence upon users’ habits and mobility has many potential applications, including resource recommendation and link prediction. Here, we construct and characterise social and place-focused graphs by using longitudinal information about declared social relationships and about users’ visits to physical places collected from a popular online location-based social service. We show that although the social and place-focused graphs are constructed from the same data set, they have quite different structural properties. We find that the social and location-focused graphs have different global and meso-scale structure, and in particular that social and place-focused communities have negligible overlap. Consequently, group inference based on community detection performed on the social graph alone fails to isolate place-focused groups, even though these do exist in the network. By studying the evolution of tie structure within communities, we show that the time period over which location data are aggregated has a substantial impact on the stability of place-focused communities, and that information about place-based groups may be more useful for user-centric applications than that obtained from the analysis of social communities alone.

Group colocation behavior in technological social networks

We analyze two large datasets from technological networks with location and social data: user location records from an online location-based social networking service, and anonymized telecommunications data from a European cellphone operator, in order to investigate the differences between individual and group behavior with respect to physical location. We discover agreements between the two datasets: firstly, that individuals are more likely to meet with one friend at a place they have not visited before, but tend to meet at familiar locations when with a larger group. We also find that groups of individuals are more likely to meet at places that their other friends have visited, and that the type of a place strongly affects the propensity for groups to meet there. These differences between group and solo mobility has potential technological applications, for example, in venue recommendation in location-based social networks.