Knowledge Encapsulation Framework (KEF)
Andrew J. Cowell, Michelle L. Gregory, Eric Marshall, Liam McGrath, and Patrick Paulson
Executive Summary
The Knowledge Encapsulation Framework (KEF) is a suite of tools to enable subject-matter experts (SME) to discover, gather, and arrange evidence and other material in support of modeling and simulation projects, as well as other domains that require collaborative workspaces for knowledge-work. The framework has multiple applications and can be used to:
Click on image to enlarge.
- Capture and investigate evidence, such as trusted material provided by the users (journal articles, government reports, etc.).
- Discover new evidence automatically (harvested from web sources, covering both traditional and social media).
- Enable collaboration and discussions through traditional wiki interaction mechanisms such as discussion tabs, synchronous chat, and social profiles.
- Automatically generate semantic annotations and relationships.
From within a wiki environment, the current KEF implementation provides a simple but powerful collaborative space for team members to review, annotate, discuss, and align evidence with their modeling frameworks. This approach allows for the combination of automatically tagged and user-vetted resources, increasing user trust in the environment, and ultimately leading to ease of adoption.
As the data repository is populated with relevant vetted material, users can interact with the data on a variety of levels depending on their goals. All data in the repository is automatically tagged with basic document metadata (source, author, date, etc.) as well as semantic information extracted from the text.
Using information extraction tools, all entities (people, locations, events, etc.) in the text are marked, as well as topics and terms regarding sentiment and rhetoric. User-identified key terms are also automatically tagged, providing a means of search and organization for ease of recall for all users in the system.
Users can correct existing annotations, or create their own to match their individual needs. The system replaces the usual manual margin mark-ups that occur with interacting with paper with electronic notes or annotations that can be searched on later or shared with other collaborators.
Impacts
KEF facilitates knowledge sharing and discussion, combined with a powerful discovery mechanism, to enable today’s knowledge workers to model complex phenomena and align evidence from both social and traditional media. KEF allows SME’s to do more with the information they already possess, while giving them access to new, potentially relevant material that would otherwise go unnoticed, providing a more holistic modeling experience.