Text Analysis
How do humanities scholars take advantage of ever-increasing amounts of textual information? This section details some of the approaches that scholars are using to analyze text using digital techniques, including stylometry, content-based analysis, and studies of metadata.
Follow the links on the right to read on. Please feel free to leave comments on each page, or to join the discussion at the end of the chapter.
Trackbacks
-
[...] This post was mentioned on Twitter by Cameron Blevins, Alex Gil and Jon Christensen, Natalie M. Houston. Natalie M. Houston said: RT @historying: Now on Tooling Up, a brief and gentle introduction to digital text analysis: http://toolingup.stanford.edu/?page_id=981 [...]
April 22, 2011: Text Mining & Analysis
Host: Matthew Jockers
I enjoyed Matthew’s seminar in text mining. I found quite remarkable the advances in stylometry based on a purely in silico analysis. It was interesting to learn how technical text and word analysis has become: different methodologies for scoring (Hamilton, Jay, Madison) were mentioned during the lecture, though unfortunately given the time constrains we couldn’t get into more details. It was also very useful to learn of the existence of end user tools like NLTK, Mallet, NLP, R- and Tapor.
From the point of view of content, I think text analysis combined with digitization of archives is going to have very important consequences: A large part of today information appears in natural language and we need to develop tools that can reliable process large quantities of information in order to obtain meaningful data.