Geography and social relationships are inextricably intertwined; the people we interact with on a daily basis almost always live near us. As people spend more time online, data regarding these two dimensions -- geography and social relationships -- are becoming increasingly precise, allowing us to build reliable models to describe their interaction. These models have important implications in the design of location-based services, security intrusion detection, and social media supporting local communities. Using user-supplied address data and the network of associations between members of the Facebook social network, we can directly observe and measure the relationship between geography and friendship. Using these measurements, we introduce an algorithm that predicts the location of an individual from a sparse set of located users with performance that exceeds IP-based geolocation. This algorithm is efficient and scalable, and could be run on a network containing hundreds of millions of users.
%0 Conference Paper
%1 backstrom2010find
%A Backstrom, Lars
%A Sun, Eric
%A Marlow, Cameron
%B International Conference on World Wide Web
%C New York, NY, USA
%D 2010
%I ACM
%K diss geo inthesis prediction proximity social spatial
%P 61--70
%R 10.1145/1772690.1772698
%T Find Me if You Can: Improving Geographical Prediction with Social and Spatial Proximity
%U http://doi.acm.org/10.1145/1772690.1772698
%X Geography and social relationships are inextricably intertwined; the people we interact with on a daily basis almost always live near us. As people spend more time online, data regarding these two dimensions -- geography and social relationships -- are becoming increasingly precise, allowing us to build reliable models to describe their interaction. These models have important implications in the design of location-based services, security intrusion detection, and social media supporting local communities. Using user-supplied address data and the network of associations between members of the Facebook social network, we can directly observe and measure the relationship between geography and friendship. Using these measurements, we introduce an algorithm that predicts the location of an individual from a sparse set of located users with performance that exceeds IP-based geolocation. This algorithm is efficient and scalable, and could be run on a network containing hundreds of millions of users.
%@ 978-1-60558-799-8
@inproceedings{backstrom2010find,
abstract = {Geography and social relationships are inextricably intertwined; the people we interact with on a daily basis almost always live near us. As people spend more time online, data regarding these two dimensions -- geography and social relationships -- are becoming increasingly precise, allowing us to build reliable models to describe their interaction. These models have important implications in the design of location-based services, security intrusion detection, and social media supporting local communities. Using user-supplied address data and the network of associations between members of the Facebook social network, we can directly observe and measure the relationship between geography and friendship. Using these measurements, we introduce an algorithm that predicts the location of an individual from a sparse set of located users with performance that exceeds IP-based geolocation. This algorithm is efficient and scalable, and could be run on a network containing hundreds of millions of users.},
acmid = {1772698},
added-at = {2017-02-02T17:16:51.000+0100},
address = {New York, NY, USA},
author = {Backstrom, Lars and Sun, Eric and Marlow, Cameron},
biburl = {https://www.bibsonomy.org/bibtex/21091139753acc807c96efc87cf4b2a75/becker},
booktitle = {International Conference on World Wide Web},
doi = {10.1145/1772690.1772698},
interhash = {a2bc307123158fb36ca1f994b8d5934c},
intrahash = {1091139753acc807c96efc87cf4b2a75},
isbn = {978-1-60558-799-8},
keywords = {diss geo inthesis prediction proximity social spatial},
location = {Raleigh, North Carolina, USA},
numpages = {10},
pages = {61--70},
publisher = {ACM},
series = {WWW '10},
timestamp = {2017-12-20T14:21:48.000+0100},
title = {Find Me if You Can: Improving Geographical Prediction with Social and Spatial Proximity},
url = {http://doi.acm.org/10.1145/1772690.1772698},
year = 2010
}