Mashing Text

Title of Study/Project:Mashing Texts

List of team members and their affiliation

  • Geoffrey Rockwell (University of Alberta)
  • Stan Ruecker (University of Alberta)
  • Stéfan Sinclair (McMaster University)
  • Susan Brown (Guelph University of Alberta)
  • Peter Organisciak (University of Alberta)

SEASR Staff Contact 
Mike Haberman - mikeh@ncsa.uiuc.edu

Procedural Outline of Study/Project

Research Question/Purpose of Study

Mashing Texts will prototype a recombinant research environment for document management, large-scale linguistic research, and cultural analysis. Mashing Texts proposes to adapt the document repository model developed for the Text Analysis Portal for Research (TAPoR) project so that a research team interested in recombinant documents can experiment with research methods suited to creating, managing and studying large collections of textual evidence for humanities research. The TAPoR project built text analysis infrastructure suited to analysis of individual texts. Mashing Texts will prototype the other side of the equation - the rapid creation of large-scale collections of evidence. It will do this by connecting available off-the-shelf open-source tools to the TAPoR repository so that the team can experiment with research using large-scale text methods.

Data Source

JiTR Text Repository

Analysis Tools

Voyeur Tools, SEASR analytic tools

Activity Timeline or Milestones

Report or Project Outcome(s)

Ideas on what your team needs from SEASR staff to help you achieve your goal.

Ideally we'd like considerable help in creating unsupervised data mining modules that could be processed with the text collections provided within JiTR. It may be preferable initially for the analytics to be invoked elsewhere (like NCSA) until we can migrate the analytic components to McMaster and/or Alberta.

Team Communication Plans

Enter labels to add to this page:
Please wait 
Looking for a label? Just start typing.