Visualization of unstructured text sequences of nursing narratives

Authors:
Shiaofen Fang;Min Lwin;Patricia Ebright
Affiliations:
Indiana University-Purdue, University Indianapolis, Indianapolis, IN;Indiana University-Purdue, University Indianapolis, Indianapolis, IN;Indiana University, Middle Drive, NU, Indianapolis, IN
Venue:
Proceedings of the 2006 ACM symposium on Applied computing
Year:
2006

Citing 4
Cited 4

LifeLines: visualizing personal histories

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Mining Text Using Keyword Distributions

Journal of Intelligent Information Systems
ThemeRiver: Visualizing Thematic Changes in Large Document Collections

IEEE Transactions on Visualization and Computer Graphics
CareView: analyzing nursing narratives for temporal trends

CHI '04 Extended Abstracts on Human Factors in Computing Systems

Term distribution visualizations with Focus+Context

Proceedings of the 2009 ACM symposium on Applied Computing
Visualizing unstructured text sequences using iterative visual clustering

VISUAL'07 Proceedings of the 9th international conference on Advances in visual information systems
Term distribution visualizations with Focus+Context

Multimedia Tools and Applications
Fingerprint matrices: uncovering the dynamics of social networks in prose literature

EuroVis '13 Proceedings of the 15th Eurographics Conference on Visualization

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a keyword-based information visualization technique for nursing record sequences. Visualizing the trend information rooted in unstructured and fragmented abstract text data is a largely unaddressed problem. In our technique, multiple hierarchical keyword based visualizations are used to explore unstructured text data from nursing records. First, each text data set is broken up into a list of keywords to enable the visualization of keyword occurrences over time and the relative distribution of keywords. A graphical user interface is provided to enable selection and classification of keywords. Users may select one or more data sets to compare, in addition to one or more groups of keywords to add to the visualization. Colors are used to distinguish quickly and easily between groups of keywords present in the visualization. At the second level of hierarchy, keywords for visualization are discovered through a predetermined automatic detection and scoring based mechanism. The aggregate frequency trend of keywords from all data sets is also provided in both hierarchies as a way to visualize overall trends and analyze various events in time.