Predicting the location of users on Twitter from low density graphs

In this paper we present an algorithm for the estimation of geographic locations of Twitter users. The algorithm is based on the graph representation of communication patterns on Twitter and employs an effective clustering algorithm for estimating locations of users from their connections in the communication graph. While using a graph based approach to estimate geo-location for Twitter users is not new, most of the existing methods require very dense networks which generally require collecting data over a considerable period of time. In this paper, we present a new method that is able to achieve good accuracy and coverage for geolocation estimation of Twitter users using a much less dense graph and only requiring a little over one month's worth of data. The approach is based on label propagation and a new inference location method that uses a clustering of geographical points. We test it on two versions of the Twitter graph built from data in June-July of 2014 and December 2014-January 2015. Analysis of the results demonstrates high accuracy - 65% of geo-labeled users have distance error between true and inferred locations less than 50 km. We were able to geolocate up 87% of users from our datasets. When comparing results between the two graphs, we show that around 40% of users move more than 25 km over the 6 month period.

[1]  Nathan Kallus,et al.  Predicting crowd behavior with big public data , 2014, WWW.

[2]  Martha Larson,et al.  The where in the tweet , 2011, CIKM '11.

[3]  Barry Wellman,et al.  Geography of Twitter networks , 2012, Soc. Networks.

[4]  David Allen,et al.  Geotagging one hundred million Twitter accounts with total variation minimization , 2014, 2014 IEEE International Conference on Big Data (Big Data).

[5]  Zoubin Ghahramani,et al.  Learning from labeled and unlabeled data with label propagation , 2002 .

[6]  Kyumin Lee,et al.  You are where you tweet: a content-based approach to geo-locating twitter users , 2010, CIKM.

[7]  Jeffrey Nichols,et al.  Home Location Identification of Twitter Users , 2014, TIST.

[8]  Lars Backstrom,et al.  Find me if you can: improving geographical prediction with social and spatial proximity , 2010, WWW '10.

[9]  Henry A. Kautz,et al.  Finding your friends and following them to where you are , 2012, WSDM '12.

[10]  David Jurgens,et al.  That's What Friends Are For: Inferring Location in Online Social Media Platforms Based on Social Relationships , 2013, ICWSM.

[11]  Ravi Kumar,et al.  Object matching in tweets with spatial models , 2012, WSDM '12.

[12]  Michelle R. Guy,et al.  Twitter earthquake detection: earthquake monitoring in a social world , 2012 .

[13]  Piet Van Mieghem,et al.  Epidemic processes in complex networks , 2014, ArXiv.

[14]  Jure Leskovec,et al.  Inferring networks of diffusion and influence , 2010, KDD.

[15]  Hiroyuki Kitagawa,et al.  Landmark-based user location inference in social media , 2013, COSN '13.

[16]  Jacob Goldenberg,et al.  Distance Is Not Dead: Social Interaction and Geographical Distance in the Internet Era , 2009, ArXiv.

[17]  Alberto Maria Segre,et al.  The Use of Twitter to Track Levels of Disease Activity and Public Concern in the U.S. during the Influenza A H1N1 Pandemic , 2011, PloS one.

[18]  Jinfei Liu.  Multiple Location Profiling for Users and Relationships from Social Network and Content , 2013 .

[19]  Fahad Bin Muhaya,et al.  Estimating Twitter User Location Using Social Interactions--A Content Based Approach , 2011, 2011 IEEE Third Int'l Conference on Privacy, Security, Risk and Trust and 2011 IEEE Third Int'l Conference on Social Computing.