The Development of a Web‐based Demographic Data Extraction Tool for Population Monitoring

Abstract

The Internet contains a great wealth of information available online. People search engines, such as WhitePages (http://www.whitepages.com), gather personal‐level demographic data, including full name, address, age and household members. Requiring only a surname and locational reference (e.g. city or postal code) as the minimum search criteria, such people search engines can be perceived as a gigantic database of demographic records. The objective of this article is to outline the development of a web‐based demographic data extraction tool for population monitoring. In this study, a web prototype was developed to extract web demographics of the Vietnamese‐American (VA) population in Texas, an ethnic minority with unique migration history, from WhitePages. After post‐processing, the personal‐level demographic data represent 40.3% of 202,003 VA in Texas reported by the American Community Survey (ACS) 2009. While all enumeration strategies, the web approach included, have their own strengths and weaknesses, this study suggests an alternative approach that is complementary to existing enumeration strategies. More research and development are needed to validate the accuracy of web demographics and further enhance data navigation and extraction rules. The utilization and release of web demographics must be cautious with regards to privacy and integrity of personal identity.

Name Recognition to Identify Patients of South Asian Ethnicity within the Cancer Registry

“…[20212228] Self-identification of ethnicity carries risks of preconceived ethnic group classification, so it is important to remember how this data is used in the context of reporting healthcare-related data. [41838]…”

“We Know Who You Are and We Know Where You Live”: A Research Agenda for Web Demographics

“…For a valid record of web demographics, the mandatory demographic attributes include a fi rst name or fi rst initial, a valid surname, and a "geocodable" address ( Word et al, n.d. ;Chow et al 2011 ) . It is not uncommon to have incomplete data that may consist of records without a full name, a name without address, or the other way around.…”

“…The basic idea is to parse the HyperText Markup Language (HTML) document and analyze the hierarchical tags embedded within the content structured in various degrees. Chow et al ( 2011 ) outlined a fi ve-step framework to automate the extraction of web demographics based on surname analysis. The process can be extended from a prede fi ned HTML schema to statistical clustering, machine-learning algorithms, data-mining techniques, or ontology-based relationships to better re fi ne the extraction and navigation rules (Chang et al 2006 ) .…”

Geovisualization of Local and Regional Migration Using Web-mined Demographics

“…An individual with different addresses would indicate a person who moved during this time. The web-based data extraction tool developed by Chow et al (2011) did not capture the information concerning when a person's demographic information was recorded, if it existed at all. Due to the absence of this temporal information, the process of determining which records received a migration label of 'Move From' or 'Move To' operated under three assumptions.…”

“…Of that population, 4.2%, or roughly 1 million, were estimated to be of Asian ethnicity (U.S. Census Bureau, 2014). Using a web-based data extraction tool that leveraged a list of popular Vietnamese surnames, Chow et al (2011) acquired demographic data for 40.3% of the estimated Vietnamese-American (VA) population in Texas as reported by the American Community Survey 2009. Chow et al (2012) used this data set to model population change during the period between 2000 and 2009 at both the county and census tract levels.…”