≡ Menu

Visualization of Large Text Corpora

In collaboration with the Digital Humanities group, we are working on ways to visualize statistical patterns in large texts. Current projects include using tags to find out what sets apart Shakespeare from his contemporaries, and viewing the effects of Samuel Johnson’s dictionary on the crystallization of the English language.

Related Publications:

Eric Alexander, Joe Kohlmann, Robin Valenza, Michael Gleicher.  Serendip: Turning Topics Back to the Text.  2013 IEEE Visualization Poster Proceedings (InfoVis ’13).

Michael Correll, Eric Alexander, Michael Gleicher.  Quantity Estimation in Visualizations of Tagged Text.  Proceedings of the 2013 ACM conference on Human Factors in Computing Systems (CHI ’13).  May 2013.

Michael Correll and Michael Gleicher.  What Shakespeare Taught Us About Text Visualization.  2012 IEEE Visualization Workshop Proceedings (2nd Workshop on Interactive Visual Text Analytics).  Oct 2012.

Michael Correll, Michael Witmore, Michael Gleicher.  Exploring Collections of Tagged Text for Literary Scholarship.  Computer Graphics Forum, 30, 3, pp. 731-740.  Jun 2011.

Point of Contact