Login / Signup

Suicide Risk and Protective Factors in Online Support Forum Posts: Annotation Scheme Development and Validation Study.

Stevie ChancellorSteven A SumnerCorinne David-FerdonTahirah AhmadMunmun De Choudhury
Published in: JMIR mental health (2021)
Our work formalizes a framework that incorporates construct validity into the development of annotation schemes for suicide risk on social media. This study furthers the understanding of risk and protective factors expressed in social media data. This may help public health programming to prevent suicide and computational social science research and investigations that rely on the quality of labels for downstream machine learning tasks.
Keyphrases
  • social media
  • public health
  • health information
  • machine learning
  • healthcare
  • working memory
  • mental health
  • big data
  • rna seq