Tailored information delivery services for open source intelligence

Open Source Intelligence (OSINT) consists of locating, harvesting, and analyzing information provided by, or available from, various public sources such as news media data, public records, academic publications, and other data sources for intelligence gathering purposes. With the advent of the internet, a plethora of unclassified freely accessible information exists across the world that provides many sources of possible intelligence value. Simultaneously this vast ocean of information creates a challenge to information systems in extracting and getting desired information from these sources. As a result, users and software systems are often overloaded with unrelated information while collecting data for open source intelligence operations. To assist in OSINT operations, we are developing a TIDS (Tailored Information Delivery Services) system to provide user selected information and reduce the amount of irrelevant information. Our TIDS system is based on semantic matching of concepts selected by users that are compared against the open source data tagged by using the same concepts. These concepts are part of a shared common ontology that can be extended through a collaborative effort of all users. As users discover new ontological instances, or concepts, they are added in an incremental process to the shared ontology, thus building a domain specific knowledge base for an OSINT operation. Furthermore, we leverage the benefits of existing upper-level ontologies for jump-starting the system. The TIDS system also provides a framework for research purposes in investigating how to best develop the components of an ontology-based information system such as semantic annotation, structure and creation of ontologies, and semantic information retrieval for the OSINT domain. The objective of our research is to create a semantics-based information delivery system that functions in a "What You Get Is What You Need (WYGIWYNTM)" fashion. Through the use of semantics matching, improved information relevancy can be achieved that supports military commanders and analysts with accurate information in their operational interests.