LAS development efforts for mission-inspired technology touch many domains ranging from tactical military, cyber, force protection, indications and warning, and large international events, such as the Rio Olympics. Topically aligned with the National Intelligence Strategy, LAS efforts also include a strong focus on direct knowledge sharing, using a variety of mechanisms to empower the analytic work force with the skills they need to succeed an environment of rapid technological advances and information saturation.

Developing the Science of Collaboration

Bev Tyler, Sharon Joines, Jessica Jameson, and Kathleen Vogel are part of a team that examine the research model employed at LAS looking for ways to optimize and replicate it for other interdisciplinary S&T collaborations. They have presented their work at conferences like the Strategic Management Society, the Society for the Social Studies of Science, and the National Communications Association. This work focuses on both the opportunities and challenges in establishing LAS at NC State and what is learned about interdisciplinary knowledge production through this real-time experiment.


Developing a Platform for Collaboration

Learning to mitigate biases requires retraining habits, deliberate practice, and opportunities to make and correct errors in a safe environment. ARA, an LAS industry partner, prototyped a serious game to help address six cognitive and social biases. In the game, the player assumes the role of a human astronaut on a space station, where a new starship crewed by a team of androids is about to launch on an important expedition. A small team of humans is being selected to command the androids. To successfully live and work among the androids, the player must demonstrate a capability for recognizing and mitigating cognitive biases, which humans apply, but androids do not.

Prototype for Sensemaking

Bard-IC is a tool that allows users to explore event data and automatically generate tailored narratives that summarize or explain this data. It operationalizes research approaches for knowledge representation and narrative discourse planning as an integrated pipeline that goes from event log data to multimedia reports. These reports can include automatically generated texts, maps, and/or videos. Bardic is implemented using the Unity 3D Engine, and uses a suite of web services running on an external server to do discourse planning, natural language generation, geospatial visualizations generation, and 3D cinematic rendering.


Bridging the gap between the art and science of analysis

Bill Boettcher and Mike Cobb presented a paper at the American Political Science Association Conference that explored the intelligence community debate between “mathematician” and “artist.” The prevailing cognitive model of the mathematicians is a modified expected utility (cost/benefit) calculus that attempts to produce optimal decisions in an information-rich world characterized by risk. The prevailing cognitive model for artists is a subjective expected utility process that attempts to produce the best decision possible in an information-poor world characterized by uncertainty. Their work starts to bridge between these perspectives—acknowledging the subjectivity of perceptions of problem components, but also the systematic nature of these departures from objective rationality.

Broadening and Enlightening Analytic Structured Tradecraft (BEAST) prototype

The intent of the Broadening and Enlightening Analytic Structured Tradecraft (BEAST) prototype is to provide a decision-centered, collaborative environment to support opportunistic, technology-enhanced structured analytic tradecraft. The BEAST v1.0 prototype integrates structured data and social media (Twitter feeds) to demonstrate the technology-enabled analytic tradecraft on a proxy problem of analysis and anticipation strategies.


Development of GazeGIS prototype

Laura Tateosian from the NC State Center for Geospatial Analytics has developed a gaze-based reading and dynamic graphic information system (GazeGIS). Location is an important component of a narrative. Mapped place names provide vital geographical, economic, historical, political, and cultural context for the text. Online sources such as news articles, travel logs, and blogs frequently refer to geographic locations, but often these are not mapped. When a map is provided, the reader is still responsible for matching references in the text with map positions. As they read a place name within the text, readers must locate its map position, then find their place again in the text to resume reading, and repeat this for each toponym. GazeGIS uses eye tracking and geoparsing to enable a more cohesive reading experience by dynamically mapping locations just as they are encountered within text.

Instrumentation of computers to improve information analysis

A collaboration between RENCI, government, and NC State researchers resulted in an instrumentation platform that is designed to understand and improve the craft of information analysis. The platform provides an extensible framework to instrument analyst’s workstations during information processing tasks. A built-in streaming data processing pipeline is included to support real-time analysis of large volumes of event data. The platform uses the latest open-source scalable and flexible web components and hardware infrastructure. Researchers are using the platform to gain insight into tool usage, analytical workflows, and collaboration patterns. The platform provides a unique, pragmatic and holistic foundation to understand the behavior of knowledge workers, and support applications assisting with information analysis.


Understanding differences in individuals and training

Allaire Welk and Christopher Mayhorn investigated investigated how individual differences and training affect performance on a medical diagnosis task. This study intended to evaluate how individual differences and training influence performance in an Internet search-based medical diagnosis task designed to simulate a intelligence analyst task. The implemented training emphasized the extraction and organization of relevant information and deductive reasoning. Preliminary results indicated that the implemented training did not significantly affect performance, however, working memory significantly predicted performance on the implemented task. These results suggest that working memory capacity influences performance on cognitively complex decision-making tasks, whereas experience with elements of the task may not.

Connect With Us

LAS aims to bring together a multi-disciplinary group of academic, industry, and government researchers, analysts and managers together to re-engineer the intelligence analysis process to promote predictive analysis. LAS will do this by conducting both classified and unclassified research in a variety of areas of research. The research done in this area will serve as the foundation for mission effects and integrated back into the enterprise.

If you would like to sign up for our email distribution list, please fill out this form: