The Library as Dataset: Text Mining at Million-Book Scale

How can academics and researchers take advantage of the large-scale digitization of texts? What tools do social scientists need in order to be able to divine knowledge from these datasets?

In this video, David Minmo (postdoctoral researcher at Princeton University, Computer Science Department) explains one promising text mining method - statistical topic modeling - and shares the result of a case study.

Love to learn? Here’re more free Yale podcasts, videos and infographics on topics in business, food, politics, art, and science »

  1. computatiohumanitatis reblogged this from kerithomasaber and added:
    (via Chaucer Girl in Aberystwyth)
  2. kerithomasaber reblogged this from yaleuniversity
  3. librarylinknj reblogged this from thelifeguardlibrarian
  4. thelifeguardlibrarian reblogged this from yaleuniversity and added:
    Sup Yale.
  5. yaleuniversity posted this