Exploiting place features in link prediction on location-based social networks

By Salvatore Scellato, Anastasios Noulas, Cecilia Mascolo. 2011

556 citations recorded by the source corpus.

Subfields: Statistical and Nonlinear Physics, Transportation, Signal Processing

How researchers see this paper

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

In Statistical and Nonlinear Physics

In Transportation

In Signal Processing

Citations in the corpus

Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries (2019, background): “Geography has been linked to the properties of online social networks (Poblete et al., 2011; Scellato et al., 2011), with the likelihood of a social link decreasing with the distance among users, with consequences for information diﬀusion (Volkovich et al., 2012).”
Mining User Mobility Features for Next Place Prediction in Location-Based Services (2012, methodology): “In particular, the additional information coming from the places visited by users has been successfully used to improve social link prediction systems [10].”
Toward Scalable Systems for Big Data Analytics: A Technology Tutorial (2014, background): “Feature-based classification methods choose a set of features for vertex-pairs and employ current link information to train a binary classifier to predict future links [229].”
Exploiting Geographical Neighborhood Characteristics for Location Recommendation (2014, background): “The available check-in data in LBSNs contain rich knowledge about users’ interests, and thus are beneﬁcial to a wide range of applications such as location recommendation [33], friend recommendation [23], and activity recommendation [34].”
Event-based social networks: linking the online and offline social worlds (2012, background): “The geographical features of users were also examined to infer social ties in [7, 26].”
DeepCity: A Feature Learning Framework for Mining Location Check-Ins (2016, background): “One direction is to use user checkins to predict friendships, such as [4, 21].”
Recommendations in location-based social networks: a survey (2015, background): “2011 [87] analyze a large set of data from Gowalla (a location-based social networking system), from which they find that the link prediction space can be reduced by 15 times by focusing on location-friends and friends-of-friends.”
Big Data: A Survey (2014, background): “Feature-based classification is to select a group of features for a vertex and utilize the existing link information to generate binary classifiers to predict the future link [139].”
On the validity of geosocial mobility traces (2013, background): “Similarly, friendship reco mmendation applications [4, 26] leverage user physical prox imity to suggest social connections.”
LCARS: a location-content-aware recommender system (2013, background): “Many recent literatures [23, 28, 6] have analyzed the interplay between users’ mobility and their online social connections.”
Link prediction in social networks: the state-of-the-art (2014, background): “Scellato et al. considered social features, place features and global features in location-based social networks for link prediction based on a supervised learning framework [74].”
Instilling Social to Physical: Co-Regularized Heterogeneous Transfer Learning (2016, background): “on social side with the help of locations (Cho, Myers, and Leskovec 2011; Scellato and Mascolo 2011), or address location or activity recommendation on physical side with the help of social media (Bhargava et al.”
Revisiting User Mobility and Social Relationships in LBSNs: A Hypergraph Embedding Approach (2019, methodology): “[28] investigated a set of hand-crafted features and showed that besides social proximity, mobility pattern similarity is also a strong indicator to predict future friendship.”
Inferring anchor links across multiple heterogeneous social networks (2013, background): “Locationbased social networks have been researched recent years [18, 25], which mainly focus on single network setting.”
GeoAI: spatially explicit artificial intelligence techniques for geographic knowledge discovery and beyond (2019, background): “have been analyzed in numerous ways with the goals of predicting human activity patterns (Scellato et al. 2011), identifying trends of temporal patterns for points of interest in cities (Sparks et al.”
"Will Check-in for Badges": Understanding Bias and Misbehavior on Location-Based Social Networks (2021, background): “…and others 2011), inferring friendship (Scellato, Noulas, and Mas-colo 2011), predicting customer volume (Georgiev, Noulas, and Mascolo 2014), measuring urban socioeconomic deprivation (Venerandi and others 2015), and even improving the efﬁciency of content delivery networks (Scellato et al. 2011).”
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”