Supporting Information Foraging by Utilizing Agents Collective Foraging Behavior
Abstract
Presently, a vast number of computational applications are developed utilizing the collective intelligence of individuals who collaborate to achieve a common goal. To achieve this goal, the members of these groups often seek information from different sources such as the web, artifacts, and other agents. The value of exploiting collective intelligence and particularly collective information seeking can be seen in myriad activities that occur across the Department of Defense. For example, intelligence agencies use federated data collections that contain millions of information fragments. To create actionable intelligence, analysts must pour through these collections and manually piece these fragments together. However, the inflow of information that this creates can quickly overwhelm even the most experienced analyst. Therefore, collective information seeking applications inherently face challenges when seeking “optimal” information. In this project, we will investigate the use of the past collective information seeking behaviors of individuals, specifically knowledge workers, to tactically reduce the overhead of finding relevant information for newcomers working on similar tasks. To understand the information seeking and foraging behavior of individuals, we will utilize Information Foraging Theory – a theory of information seeking that has been applied successfully to diverse domains such as web, interfaces and programming. Current Information Foraging Theory models account for individual forager’s information foraging behavior in isolation. We will extend the data model of Information Foraging Theory to capture the foraging behaviors, including the costs and values of different artifacts to different foragers on different tasks, then create data models that capture the collective mental models of groups of individuals, and develop an unsupervised prediction algorithm based on these mental models and using these predictions to make recommendations to an individuals based on their foraging history. We believe this approach will help in utilizing the collective foraging wisdom of the crowd to make better foraging recommendations.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Jan 21, 2022
- Source ID
- FA95502110108
Entities
People
- Sandeep Kaur Kuttal
Organizations
- Air Force Office of Scientific Research
- United States Air Force
- University of Tulsa