期刊名称：GI_FORUM - Journal for Geographic Information Science
电子版ISSN：2308-1708
出版年度：2014
页码：30-39
DOI：10.1553/giscience2014s30
出版社：ÖAW Verlag, Wien
摘要：An understanding of people’s travel behavior is important for a functional design oftransportation networks. This paper explores the use of georeferenced tweets for extractingaggregated travel patterns, i.e. describing the routes that people travel on a given day fromorigin to destination. The focus is on terrestrial long-distance travel, expanding over morethan 100km. The study uses georeferenced tweets collected over four weeks for a testregion in Austria and one in Florida. It applies selection filters to extract tweets that containpotentially useful information about users moving between different cells of the testregions. Further the mean travel direction for each grid cell is computed for different daysand analyzed. The study also explores the use of a space-time permutation model to identifyspatio-temporal clusters of tweets and their change over time.
