Download Full Text (1.2 MB)


The goal of this project is to design a visualization system for information extracted from large amounts of unstructured text. The importance of the project is for the system to display information in a more informative way than simple highlighting of the raw text. The data is obtained from a program that scans multiple files for entities and extracts the information in said files pertaining to those entities. The entities that the program scans for includes people, organizations, locations, dates, incidents and any relative key words. The information is extracted and stored in JSON files, specifically in a format that can be recognized by the visualization tool. The tool used is Exhibit 3.0 by Simile Widgets and is shown below, Figure 1 displaying the map and Figure 2 comparing the points. Exhibits displays the inputted data out on a map, using plots to show which locations had more frequent occurrences. The anticipated results are that the visualization system allows researchers to better understand the information being returned.

Publication Date



computer science, visualization systems


Computer Engineering | Engineering

Faculty Advisor/Mentor

Bridget McInnes

VCU Capstone Design Expo Posters


© The Author(s)

Date of Submission

July 2015

Visualization of NLP Extractions