Spatial mining of migration patterns from web demographics. Issue 10 (3rd October 2018)

• Record Type: Journal Article
• Authors: Chow, T. Edwin; Schuermann, Ryan T; Ngu, Anne H; Dahal, Khila R
• Is Part Of: International journal of geographical information science. Volume 32:Issue 10(2018)
• Page Start: 1977
• Page End: 1998
• Publication Date: 2018-10-03
• Subjects: Web census -- demographic analysis -- small area geography -- migration -- Internet microdata; Geography -- Data processing -- Periodicals; Information storage and retrieval systems -- Periodicals; Géomatique -- Périodiques; Systèmes d'information -- Périodiques; 910.285
• DOI: 10.1080/13658816.2018.1470633
• Languages: English
• ISSNs: 1365-8816

Abstract

ABSTRACT: Volunteered Geographic Information, social media, and data from Information and Communication Technology are emerging sources of big data that contribute to the development and understanding of the spatiotemporal distribution of human population. However, the inherent anonymity of these crowd-sourced or crowd-harvested data sources lack the socioeconomic and demographic attributes to examine and explain human mobility and spatiotemporal patterns. In this paper, we investigate an Internet-based demographic data source, personal microdata databases publicly accessible on the World Wide Web (hereafter web demographics), as potential sources of aspatial and spatiotemporal information regarding the landscape of human dynamics. The objectives of this paper are twofold: (1) to develop an analytical framework to identify mobile population from web demographics as an individual-level residential history data, and (2) to explore their geographic and demographic patterns of migration. Using web demographics of Vietnamese–Americans in Texas collected in 2010 as a case study, this paper (1) addresses entity resolution and identifies mobile population through the application of a Cost-Sensitive Alternative Decision Tree (CS-ADT) algorithm, (2) investigates migration pathways and clusters to include both short- and long-distance patterns, and (3) analyze the demographic characteristics of mobile population and the functional relationship with travel distance. By linking the physical space at the individual level, this unique methodology attempts to enhance the understanding of human movement at multiple spatial scales.