Authors:Markus John1;Florian Heimerl2;Ba-Anh Vu1 andThomas Ertl1
Affiliations:1University of Stuttgart, Germany;2University of Wisconsin-Madison, United States
Keyword(s):Exploratory Visual Text Analytics, Digital Humanities, Document Visualization, Natural Language Processing.
RelatedOntology Subjects/Areas/Topics:Abstract Data Visualization ;Computer Vision, Visualization and Computer Graphics ;Text and Document Visualization ;Visual Data Analysis and Knowledge Discovery
Abstract:Interactive text visualization can help users explore and gain insights into complex and often large document sets. One popular visualization strategy to represent such collections is to depict each document as a glyph in 2D space. These spaces have proven effective, especially when combined with interactive exploration methods. However, current exploratory approaches are largely limited to single areas of a 2D spatialization, lacking support for important comparative exploration and analysis tasks. In this paper, we extend a flexible focus+context exploration technique to tackle this challenge. In particular, based on practical tasks from the digital humanities, we focus on exploring and investigating relationships between entities in large document collections. Our approach uses natural language processing to extract characters and places, including information about their relationships. We then use linked views to facilitate visual analysis of extracted information artifacts. Based on two usage scenarios, we demonstrate successful applications of the approach and discuss its benefits and limitations.(More)
Interactive text visualization can help users explore and gain insights into complex and often large document sets. One popular visualization strategy to represent such collections is to depict each document as a glyph in 2D space. These spaces have proven effective, especially when combined with interactive exploration methods. However, current exploratory approaches are largely limited to single areas of a 2D spatialization, lacking support for important comparative exploration and analysis tasks. In this paper, we extend a flexible focus+context exploration technique to tackle this challenge. In particular, based on practical tasks from the digital humanities, we focus on exploring and investigating relationships between entities in large document collections. Our approach uses natural language processing to extract characters and places, including information about their relationships. We then use linked views to facilitate visual analysis of extracted information artifacts. Based on two usage scenarios, we demonstrate successful applications of the approach and discuss its benefits and limitations.