@Article{info:doi/10.2196/jmir.9.1.e4,
author="Zeng, Qing T
and Tse, Tony
and Divita, Guy
and Keselman, Alla
and Crowell, Jon
and Browne, Allen C
and Goryachev, Sergey
and Ngo, Long",
title="Term Identification Methods for Consumer Health Vocabulary Development",
journal="J Med Internet Res",
year="2007",
month="Mar",
day="14",
volume="9",
number="1",
pages="e4",
keywords="Consumer health information; vocabulary; natural language processing",
abstract="Background:  The development of consumer health information applications such as health education websites has motivated the research on consumer health vocabulary (CHV). Term identification is a critical task in vocabulary development. Because of the heterogeneity and ambiguity of consumer expressions, term identification for CHV is more challenging than for professional health vocabularies. Objective:  For the development of a CHV, we explored several term identification methods, including collaborative human review and automated term recognition methods. Methods:  A set of criteria was established to ensure consistency in the collaborative review, which analyzed 1893 strings. Using the results from the human review, we tested two automated methods---C-value formula and a logistic regression model. Results:  The study identified 753 consumer terms and found the logistic regression model to be highly effective for CHV term identification (area under the receiver operating characteristic curve = 95.5{\%}). Conclusions:  The collaborative human review and logistic regression methods were effective for identifying terms for CHV development. ",
issn="1438-8871",
doi="10.2196/jmir.9.1.e4",
url="http://www.jmir.org/2007/1/e4/",
url="https://doi.org/10.2196/jmir.9.1.e4",
url="http://www.ncbi.nlm.nih.gov/pubmed/17478413"
}