Detecting substance-related problems in narrative investigation summaries of child abuse and neglect using text mining and machine learning.

Journal: Child abuse & neglect
Published Date: Dec 1, 2019

Abstract

BACKGROUND: State child welfare agencies collect, store, and manage vast amounts of data. However, they often do not have the right data, or the data is problematic or difficult to inform strategies to improve services and system processes. Considerable resources are required to read and code these text data. Data science and text mining offer potentially efficient and cost-effective strategies for maximizing the value of these data.

Authors

  • Brian E Perron
    Child and Adolescent Data Lab, University of Michigan, School of Social Work, 1080 S University Ave, Ann Arbor, MI, 48109, United States. Electronic address: beperron@umich.edu.
  • Bryan G Victor
    Indiana University School of Social Work, 902 West New York Street Indianapolis, Indiana, 46202, United States.
  • Gregory Bushman
    Child and Adolescent Data Lab, University of Michigan, School of Social Work, 1080 S University Ave, Ann Arbor, MI, 48109, United States.
  • Andrew Moore
    Child and Adolescent Data Lab, University of Michigan, School of Social Work, 1080 S University Ave, Ann Arbor, MI, 48109, United States.
  • Joseph P Ryan
    Child and Adolescent Data Lab, University of Michigan, School of Social Work, 1080 S University Ave, Ann Arbor, MI, 48109, United States.
  • Alex Jiahong Lu
    Child and Adolescent Data Lab, University of Michigan, School of Social Work, 1080 S University Ave, Ann Arbor, MI, 48109, United States; University of Michigan, School of Information, 105 S State St, Ann Arbor, MI, 48109, United States.
  • Emily K Piellusch
    Child and Adolescent Data Lab, University of Michigan, School of Social Work, 1080 S University Ave, Ann Arbor, MI, 48109, United States.

Keywords

External Resources

Popular Topics
Recent Journals