Generalizing Text to Protect Privacy

pdf

Textual data can contain highly sensitive and identifying information; redaction is a difficult process that can make text unreadable and useless for many purposes. This poster describes an alternative: using ontologies to generalize words, resulting in text that is less sensitive, but still preserves meaning in a way that redacted data does not.

  • Ontologies
  • privacy
  • Purdue University
  • Text Mining
  • 1012208
  • SaTC PI Meeting 2012
  • Poster
  • Academia
  • SaTC Posters
Submitted by Katie Dey on