A Semi-Automated Interpretation Tool for Socio-Cultural Data Collection

Mahoney1, S., Pfautz2, J., Campolongo1, J., and Thomsen2, E.

Proceedings of Human Social Culture Behavior (HSCB) Focus 2011, Chantilly, VA (February 2011)

Despite an increased emphasis on understanding social and cultural phenomena as part of current military engagements, existing tools to support social network construction and analysis are only in limited use by those with most frequent and extensive contact with local populations – military intelligence analysts supporting tactical operations. While collecting intelligence and deriving hypotheses in the kinetic domain follows a consistent and familiar process, collection and analysis in the socio-cultural information domain occurs within shifting contexts (e.g., local customs, economics, etc.), which may be unknown to the average soldier and even only partially understood by experts. An analyst needs to be able to exploit information collection capabilities at lower echelons to help form complex, multi-context social networks that, in turn, can inform more sophisticated analysis by individual domain specialists and decision makers. As a result, we are building a tool to support this type of data collection and interpretation, based on a highly flexible knowledge representation, LC Typing, which provides computational deductive inference flexibility, and serves as the foundation of a hierarchical heuristic interpretation process. This interpretation process can be driven by experts and executed by novices. In this presentation, we will provide an overview of this interpretation process along with examples of types of data that can be ingested, inferred (interpreted) information, and resulting social network contributions our approach will support.

1 Charles River Analytics

2 DSS Lab

For More Information

To learn more or request a copy of a paper (if available), contact J. Campolongo.

(Please include your name, address, organization, and the paper reference. Requests without this information will not be honored.)