Skip to Main Content U.S. Department of Energy
IN-SPIRE™ Visual Document Analysis


Collage of the IN-SPIRE™ Visual Interface

People have the natural ability to rapidly comprehend visual images. To make the most of this skill, researchers at PNNL have developed IN-SPIRE™ and other creative and powerful approaches to present different kinds of data in visual displays.

IN-SPIRE™ can quickly and automatically convey the gist of large sets of unformatted text documents such as technical reports, web data, newswire feeds and message traffic. IN-SPIRE™ can handle real-time data by adding new documents as they arrive. It also processes foreign language data and provides robust support for translation. By clustering similar documents together, this Windows-based software unveils common themes and reveals hidden relationships within the collection. IN-SPIRE™ allows analysts to spend more time exploring the information they find most relevant and less time sifting through the masses of irrelevant documents.

IN-SPIRE™ analyzes a multitude of text files and determines key topics or themes in each to create a signature for each document in the collection. IN-SPIRE's two main visualizations display representations of the documents in which those with similar or related topics appear closer together. The Galaxy visualization uses the metaphor of the stars in the night sky with each star representing an individual document. The ThemeView™ visualization uses a 3-dimensional terrain map display to provide a high-level overview of the data.

Search tools in IN-SPIRE™ support simple queries, phrase queries, and queries with example text. Other tools help to explore trends over time and relationships between concepts. All of the tools in IN-SPIRE™ leverage the power of the Galaxy and ThemeView™ visualizations.