It's the way you check-in: identifying users in location-based social networks

By Luca Rossi, Mirco Musolesi. 2014

82 citations recorded by the source corpus.

In recent years, the rapid spread of smartphones has led to the increasing popularity of Location-Based Social Networks (LBSNs). Although a number of research studies and articles in the press have shown the dangers of exposing personal location data, the inherent nature of LBSNs encourages users to publish information about their current location (i.e., their check-ins). The same is true for the majority of the most popular social networking websites, which offer the possibility of associating the current location of users to their posts and photos. Moreover, some LBSNs, such as Foursquare, let users tag their friends in their check-ins, thus potentially releasing location information of individuals that have no control over the published data. This raises additional privacy concerns for the management of location information in LBSNs. In this paper we propose and evaluate a series of techniques for the identification of users from their check-in data. More specifically, we first present two strategies according to which users are characterized by the spatio-temporal trajectory emerging from their check-ins over time and the frequency of visit to specific locations, respectively. In addition to these approaches, we also propose a hybrid strategy that is able to exploit both types of information. It is worth noting that these techniques can be applied to a more general class of problems where locations and social links of individuals are available in a given dataset. We evaluate our techniques by means of three real-world LBSNs datasets, demonstrating that a very limited amount of data points is sufficient to identify a user with a high degree of accuracy. For instance, we show that in some datasets we are able to classify more than 80% of the users correctly.

Subfields: Artificial Intelligence, Sociology and Political Science, Transportation

How researchers see this paper

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

In Artificial Intelligence

In Sociology and Political Science

In Transportation

Citations in the corpus

Knock Knock, Who's There? Membership Inference on Aggregate Location Data (2017, background): “Previous location privacy research taking into account traces or profiles of single users [7, 12, 16, 24, 28, 37] does not apply to our problem, which focuses on aggregate location statistics.”