Topic Visualization

In collaboration with the Center for Machine Learning and Intelligent Systems at UC Irvine, we have developed TopicNets. The tool is an application of the core WiGis framework to the task of information discovery across large document sets. TopicNets works by extracting "Topics"-- sets of associated terms with probability and confidence values, from large documents or document sets. An interactive WiGi graph is then generated, showing document-topic (and/or section-topic) relationships across the large data set.

Video

Features

This system has a lot of nice data discovery features. For example:

1: iterative text-based search and result visualization. This allows users to quickly drill-down to fine grained details on complex queries.

2: Temporal Layout --lay out a single document or set of documents on a timeline

3: Topic-based Deformation, deform the linear structure (paragraphs, sections etc) of a text based on topics that they contain

4: Color Association and bleeding. Individual nodes (eg: document authors) can be colored in a customized scheme. Colors can be bled across the document-topic edges, and topic nodes assume a blend of color from associated nodes.

5: Multidimensional Scaling Layout based on a topic-similarity matrix.