Thursday, April 12, 2012

Text analysis and visualization




Many Eyes
you will need: an account at ManyEyes




  
FIND: a (machine-readable) text
State of the Union Addresses: American Presidency Project

MASSAGE: clean it up, if need be

UPLOAD: copy and paste
VISUALIZE
We will make five visualizations:
  1. Word Cloud,
  2. Word Tree,
  3. Phrase Net,
  4. Tag Cloud,
  5. and then a second Tag Cloud that compares 2009 and 2012.
SHARE
We will embed one of those visualization in our blog.


What if I want to compare more than two texts?
(e.g. 2009, 2010, 2011, 2012
)


Voyant/Voyeur

http://voyeurtools.org/





 


We will upload four texts, and compare them.
We will explore some other Voyeur visualizations, e.g. Bubblelines.

FIND: a (machine-readable) text(s)
Voyeur accepts a URL, plain-text, HTML, XML, and (some) PDFs.
State of the Union Addresses: American Presidency Project

MASSAGE: or download these
UPLOAD:
VISUALIZE:

SHARE: 


Other activities:

1. Project Gutenberg's State of Union Addresses corpus.  Use the URL for the HTML version and Voyant will upload it. 









    No comments:

    Post a Comment