Alex Endert (Professor) Arjun Srinivasan Brad Thwaites
PUNGA, short for Provenance-supported Undirected Node Graph Analytics is a tool for intelligence analysts. PUNGA assists analysts in making sense of a large textual-based dataset by supporting data processing (Named Entity Recognition), data cleaning, data analysis, and analytic provencance.
PUNGA provides users the ability to combine, format, clean the data as per their convenience before and during analysis with the Entity View. PUNGA also facilitates user interaction with the data sets in a number of linked views. These visualizations include the Document Viewer, the Node Graph View, and the Calendar View. Finally, PUNGA provides a Provenance View that displays quantitative values that summarize the analysis session and more importantly help in analytic provenance.
Our team relied on the Stanford NLP Library for the Named Entity Recognition of the dataset which we processed beforehand. We also relied heavily on D3.js for PUNGA's visualizations and jQuery for just about everything else.
Please watch the video below for a demo of PUNGA.
Our team plans to continue work on PUNGA in preparation for a VAST submission. We would like to improve the brushing on the Provenance View. We would also like to provide a more graceful transition from Analysis to Entity View - preserving the user's context. Finally, we would have liked to expose our tool to more users to see how they react and also to determine which actions carry the most weight for the Provenance View.