Please use this identifier to cite or link to this item:

Twitter Connections Shaping New York City

File Size Format  
paper0127.pdf 3.26 MB Adobe PDF View/Open

Item Summary Sobolevsky, Stanislav Kats, Philipp Malinchik, Sergey Hoffman, Mark Kettler, Brian Kontokosta, Constantine 2017-12-28T00:43:38Z 2017-12-28T00:43:38Z 2018-01-03
dc.identifier.isbn 978-0-9981331-1-9
dc.description.abstract Geo-tagged Twitter has been proven to be a useful proxy for urban mobility, this way helping to understand the structure of the city and the shape of its local neighborhoods. In the present work we approach this problem from another angle by leveraging additional information on Twitter customers mentioning each other, which might partially reveal their social relations. We propose a novel way of constructing a spatial social network based on such data, analyze its structure and evaluate its utility for delineating urban neighborhoods. This delineation happens to have substantial similarity to the earlier one based on the user mobility network. It leads to an assumption that the social connectivity between the users is strongly related with the similarity in their mobility patterns. We justify this hypothesis enabling extrapolation of the available user mobility patterns as a proxy for social connectivity and building a network of hidden ties based on the mobility pattern similarity. Finally, we evaluate the socio-economic characteristics of the partitions for all three networks of all mentioning, reciprocal mentioning and the hidden ties.
dc.format.extent 9 pages
dc.language.iso eng
dc.relation.ispartof Proceedings of the 51st Hawaii International Conference on System Sciences
dc.rights Attribution-NonCommercial-NoDerivatives 4.0 International
dc.subject Deep Learning, Ubiquitous and Toy Computing
dc.subject Human mobility, social networks, big data, social media, community detection
dc.title Twitter Connections Shaping New York City
dc.type Conference Paper
dc.type.dcmi Text
dc.identifier.doi 10.24251/HICSS.2018.127
Appears in Collections: Deep Learning, Ubiquitous and Toy Computing

Please email if you need this content in ADA-compliant format.

This item is licensed under a Creative Commons License Creative Commons