Your browser doesn't support javascript.
loading
Integrating topic modeling and word embedding to characterize violent deaths.
Arseniev-Koehler, Alina; Cochran, Susan D; Mays, Vickie M; Chang, Kai-Wei; Foster, Jacob G.
Affiliation
  • Arseniev-Koehler A; Department of Sociology, University of California, Los Angeles, CA 90095.
  • Cochran SD; Bridging Research Innovation, Training and Education for Science, Research & Policy Center, University of California, Los Angeles, CA 90095.
  • Mays VM; Bridging Research Innovation, Training and Education for Science, Research & Policy Center, University of California, Los Angeles, CA 90095.
  • Chang KW; Department of Epidemiology, Fielding School of Public Health, University of California, Los Angeles, CA 90095.
  • Foster JG; Department of Statistics, University of California, Los Angeles, CA 90095.
Proc Natl Acad Sci U S A ; 119(10): e2108801119, 2022 03 08.
Article in En | MEDLINE | ID: mdl-35239440
ABSTRACT
SignificanceWe introduce an approach to identify latent topics in large-scale text data. Our approach integrates two prominent methods of computational text

analysis:

topic modeling and word embedding. We apply our approach to written narratives of violent death (e.g., suicides and homicides) in the National Violent Death Reporting System (NVDRS). Many of our topics reveal aspects of violent death not captured in existing classification schemes. We also extract gender bias in the topics themselves (e.g., a topic about long guns is particularly masculine). Our findings suggest new lines of research that could contribute to reducing suicides or homicides. Our methods are broadly applicable to text data and can unlock similar information in other administrative databases.
Subject(s)
Key words

Full text: 1 Collection: 01-internacional Database: MEDLINE Main subject: Violence / Databases, Factual / Homicide / Models, Theoretical Type of study: Prognostic_studies Limits: Humans Country/Region as subject: America do norte Language: En Journal: Proc Natl Acad Sci U S A Year: 2022 Type: Article

Full text: 1 Collection: 01-internacional Database: MEDLINE Main subject: Violence / Databases, Factual / Homicide / Models, Theoretical Type of study: Prognostic_studies Limits: Humans Country/Region as subject: America do norte Language: En Journal: Proc Natl Acad Sci U S A Year: 2022 Type: Article