Exploring and Visualizing Frequent Patterns in
Text Collections with FeatureLens

Jump to: Participants Publications  Sponsors

Project description

FeatureLens is an interface to explore and visualize features in collections of text documents. It allows the exploration of frequent patterns found in the text: e.g. frequently used words but also frequent patterns of ngrams which leads to the discovering of fuzzy repetition patterns. FeatureLens integrates the results of text-mining algorithms into a meaningful representation of a text collection. Features can be compared, and occurences of the patterns are shown in the text. To help users in finding interesting patterns FeatureLens highlights features that have specific patterns of use in the collection (increasing, decreasing, spike behavior etc.

Participants

Anthony Don, Post-doc fellow (visiting from Labri, University Bordeaux I, France)
Catherine Plaisant, PhD, Associate Research Scientist, HCIL
Ben Shneiderman, PhD, Professor, Computer Science

Elena Zheleva, Machon Gregory, Sureyya Tarkan (Graduate Students, Computer Science, students of Ben Shneiderman's Information Visualization class project who worked with Anthony on developping FeatureLens as part of their class project.

Tanya Clement (PhD Graduate Student, English Department)
Loretta Auvil and Amit Kumar (collaborators from NCSA, U. of Illinois)

We also appreciate the feedback and suggestions of Celeste Paul, Matt Kirschenbaum and others from the MONK project and MITH the Maryland Institute for Technology in the Humanities

Visuals

Slides from Catherine's 2007 HCIL symposium talk, with example of use

Long VIDEO Demo: Part-1 ; Part-2 ; Part-3 ; Part-4 ;

Example with Shakespeare collection(running on MONK Project server, NOT WORKING ANYMORE )
Example with Early American Fiction collection (running on MONK Project server, NOT WORKING ANYMORE )

Our submission to "Visualizing 'Gamer Theory 2.0'

Publications and reports

Don, A., Zheleva, E., Gregory, M., Tarkan, S., Auvil, L., Clement, T., Shneiderman, B., Plaisant, C.
Discovering interesting usage patterns in text collections: integrating text mining with visualization
Proceedings of the sixteenth ACM conference on Conference on information and knowledge management, 2007, p. 213 - 222
[PDF]

The original work in Featurelens also led to the Master Thesis of Mashon Gregory and this paper: Shape Identification in Temporal Data Sets, in Expanding the Frontiers of Visual Analytics and Visualization, Springer, 2012, pp 305-321

Featurelens is also mentionned in :

Visualizing Repetition in Text." Stan Ruecker, Milena Radzikowska, Piotr Michura, Carlos Fiorentino and Tanya Clement. CHWP A.46, publ. July 2008.

A thing not beginning and not ending': using digital tools to distant-read Gertrude Stein's The Making of Americans. Tanya E. Clement. Literary and Linguistic Computing 2008 23(3):361-381; doi:10.1093/llc/fqn020

"The Story of One: Humanity scholarship with visualization and text analysis," Clement, T., Plaisant, C., Vuillemot, R. Proceedings of the Digital Humanities Conference (DH 2009).

Sponsors and Partners

The project is conducted in collaboration the Maryland Institute for Technologies in the Humanities (MITH). We appreaciate support from the Andrew W. Mellon foundation as part of the MONK project

Other relevant HCIL pages

BasketLens
Other HCIL Visualization projects

Web Accessibility