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

IN-SPIRE™ Visual Document Analysis

Overwhelmed with information but can't make heads or tails out of it? Industry and government face this challenge every day as they try to stay ahead of the competition or understand national security risks.

The ability to uncover relationships, trends, and themes hidden within data can lead to new knowledge and new insights that could be used to assess terrorist threats, determine how to treat a medical condition, or gather market research on the competition.

IN-SPIRE™, powerful information visualization software developed by Pacific Northwest National Laboratory, can give people the ability to see something different in the data they already have. Learn more about IN-SPIRE

Latest Version: IN-SPIRE Version 5.9

Recent New Tools

  • Charged Terms (5.9): The Charged Terms panel of the Lexical Analysis tool provides a quick way to see the most charged keywords, extracted entities, and highlighted groups for a given axis of the measured lexical axis. This is a great tool to use during your initial exploration of a dataset to find keywords or entities you may not have previously considered
  • .
  • Time and Number Groups (5.9): The Search Network tool now has a quick way to create groups that split a time interval or a number interval into evenly distributed groups. For example, in the picture above, there would be 6 new groups created, one for each month between February and July (inclusive) for the year 2011. The same can be applied to number intervals, enabling the creation of groups that span number ranges, like 0-100, 100-200, 200-300, etc. The intervals and number of groups for time and number groups is customizable in the user interface.
  • Context Sensitive Help (5.9): The tools and visualizations of IN-SPIRE now contain help icons in the upper-right corner of each window, providing context-sensitive links to documents in the help system. These menus can also be customized to provide access to site-specific documentation on each tool.
  • Time Tool Enhancements (5.9): The Flows tool has been updated to provide finer control over which flows are displayed in the visualization. A right click menu has been added that provides additional operations, including hiding a particular group. Additionally, in the Now Showing menu for the Flows tool, an additional menu option for Highlighted Groups which only shows flows for groups highlighted in the groups widget. This also gives the added benefit of showing groups from multiple group folders in the visualization.
  • Lines vs. Bars (5.9): The menu option in the Time tool for selecting Line Graphs vs. Bar Graphs is now "sticky" and your selection is remembered between sessions of IN-SPIRE. Additionally, this setting takes effect across all tools, including Facets and the Time widget in the upper-left corner of the screen.
  • Focus and Ignore (5.8): Starting in version 5.8, the Focus and Ignore sidebar widget allows you to Create an "instant subset" of a specific set of documents (from selection or groups), as if they were the only ones in the dataset; Ignore (remove from calculations and search) any documents you consider to be "outliers" or "junk"; Return to a previous focus operation in one click without losing your ignored documents. Once a document has been acted upon from the Focus & Ignore widget, all of the tools in the system will react accordingly. For example, in a dataset about Topics A, B, and C, if you focus on all of the documents in Topic A, the documents for B and C will be temporarily removed from the dataset, and IN-SPIRE will recalculate terms, themes, group memberships, etc. This allows you to get more detailed terms and themes about Topic A, without the terms from the documents in B and C contributing to the calculation. The documents in B and C also will not be returned in search results.
  • Enhanced Lexical Support and Phrase Boosting (5.8): Starting in 5.8 you can add a list of terms related to your domain and measure your documents against them. Watch a video about Lexical Analysis You can also alter the way IN-SPIRE treats multi-word phrases; useful in technical documents.Watch a video about Phrase Boosting
  • Numeric Themeview Classic (5.8): If your dataset has a numeric categorical field, you can use it as the basis for generating a Themeview visualization, using several statistical measures.
  • Facets (5.8): Facets enable analysts to quickly drill down and identify document sets based upon their membership in any collection of IN-SPIRE groups. Watch a video about Facets.
  • Time (5.8): The "Time Slicer" has been replaced by the "Time" tool and offers a more intuitive and responsive user experience. Watch a video about the Time Tool.
  • Term Details (5.8): Terms found within the Summary tool, Time, or Document Viewer can be inspected to reveal additional information such as related terms and their temporal distribution profiles.

Recent New Algorithms (5.8)

  • Entity Extraction: IN-SPIRE comes bundled with an entity extractor that extracts People, Organizations, Locations, E-mail addresses, web addresses, and more.
  • Automatic Keyword Extraction: Essential keywords and phrases are now automatically identified and extracted when documents are processed by IN-SPIRE, enabling keywords and phrases such as "united states", "supreme court", and "pope benedict."
  • Themes: Keywords and phrases are grouped into themes based on their co-occurrence within documents in a dataset.
  • Surprising Terms: The Time tool's terms view uses a new algorithm to analyze change in term frequency over time. All terms in the document content are analyzed to find those with interesting spikes in frequency.