Recorded: 05/01/2020

Presenter: Joshua Been, Director of Data & Digital Scholarship

Intro and Outro Music: Michael Thompson, Assistant Director for Library Collections

Description: This webinar will will demonstrate how to assign parts of speech (POS) tags to a corpus of multiple texts and then to mine this content using the POS tags. Specifically, we will identify verbs and then search for nearby subjects.

Practice datasets: DOWNLOAD

Online Resources Referenced:

• English Penn Treebank part-of-speech Tagset
• Software & Tools:
• AntConc
• TagAnt
  
• Subject-Verb-Object Identification Python Script on Google Colab