Social Activity Hubs: Estimating User Specific Contextual Factors from Social Media Data

Context influences sociopolitical attitudes and behaviors, making the estimation of individuals' contexts an important methodological problem for the social sciences. We add to this body of work by presenting a method to estimate an individual's spatial contexts, specifically the set of geospatial areas an individual is most active in. Our approach, which utilizes the Dirichlet process mixture model, departs most significantly from more traditional approaches to estimating relevant spatial locations in that it does not arbitrarily constrain the number of spatial contexts an individual can have. This modeling approach reflects our recognition that an individual's lived experiences is a combination of different contexts that overlap to varying degrees. This flexibility therefore yields a more valid measure of spatial contexts. To illustrate our method, including its performance relative to other measures, we apply our method to Twitter data generated by protesters who participated in the 2015 Freddie Gray protests in Baltimore, MD.

[1]  Kimberley S. Johnson.  White Flight: Atlanta and the Making of Modern Conservatism , 2007, Perspectives on Politics.

[2]  Pablo Barberá.  Birds of the Same Feather Tweet Together: Bayesian Ideal Point Estimation Using Twitter Data , 2015, Political Analysis.

[3]  Melissa L. Sands.  Exposure to inequality affects support for redistribution , 2017, Proceedings of the National Academy of Sciences.

[4]  Andrea H. Tapia,et al.  Social Triangulation: A new method to identify local citizens using social media and their local information curation behaviors , 2017, ISCRAM.

[5]  Maria Abascal.  Us and Them , 2015 .

[6]  Ryan D. Enos.  Causal effect of intergroup contact on exclusionary attitudes , 2014, Proceedings of the National Academy of Sciences.

[7]  Radford M. Neal.  Markov Chain Sampling Methods for Dirichlet Process Mixture Models , 2000 .

[8]  Christopher J. Fariss,et al.  Who Protests ? Using Social Media Data to Estimate How Social Context Affects Political Behavior , 2017 .

[9]  Mark D. Stevenson,et al.  Spatial targeting of infectious disease control: identifying multiple, unknown sources , 2014 .

[10]  D. Rubin,et al.  Inference from Iterative Simulation Using Multiple Sequences , 1992 .

[11]  Michelle V. Hauge,et al.  Tagging Banksy: using geographic profiling to investigate a modern art mystery , 2016 .

[12]  Zachary C. Steinert-Threlkeld.  Spontaneous Collective Action: Peripheral Mobilization During the Arab Spring , 2017, American Political Science Review.

[13]  Kyle Crowder,et al.  The Racial Context of White Mobility: An Individual-Level Assessment of the White Flight Hypothesis , 2000 .

[14]  Bin Jiang,et al.  Volunteered Geographic Information: Towards the establishment of a new paradigm , 2015, Comput. Environ. Urban Syst..

[15]  Satish V. Ukkusuri,et al.  Understanding urban human activity and mobility patterns using large-scale location-based data from online social media , 2013, UrbComp '13.

[16]  Jason J. Jones,et al.  The paradox of weak ties in 55 countries , 2017 .

[17]  W. Shadish,et al.  Campbell and Rubin: A primer and comparison of their approaches to causal inference in field settings. , 2010, Psychological methods.

[18]  Cameron Marlow,et al.  A 61-million-person experiment in social influence and political mobilization , 2012, Nature.

[19]  Nathan D. Woods,et al.  The Mobilizing Effect of Majority–Minority Districts on Latino Turnout , 2004, American Political Science Review.

[20]  T. Zeitzoff,et al.  Terrorism and Voting: The Effect of Rocket Threat on Voting in Israeli Elections , 2014, American Political Science Review.

[21]  Alessandro Vespignani,et al.  Online social networks and offline protest , 2015, EPJ Data Science.

[22]  W. Shadish,et al.  Experimental and Quasi-Experimental Designs for Generalized Causal Inference , 2001 .

[23]  D. Kim Rossmo,et al.  Geographic Profiling , 2017, Encyclopedia of GIS.

[24]  D. Lazer,et al.  Data ex Machina: Introduction to Big Data , 2017 .

[25]  Christopher J. Fariss,et al.  Enhancing Validity in Observational Settings When Replication Is Not Possible , 2018 .

[26]  Leland Gerson Neuberg,et al.  A solution to the ecological inference problem: Reconstructing individual behavior from aggregate data , 1999 .

[27]  Mike O'Leary,et al.  Implementing a Bayesian approach to criminal geographic profiling , 2010, COM.Geo '10.

[28]  Ryan D. Enos,et al.  Intergroup Behavioral Strategies as Contextually Determined: Experimental Evidence from Israel , 2016, The Journal of Politics.

[29]  Ryan D. Enos.  What the Demolition of Public Housing Teaches Us about the Impact of Racial Threat on Political Behavior , 2016 .

[30]  David E. Broockman,et al.  Durably reducing transphobia: A field experiment on door-to-door canvassing , 2016, Science.