Languaged Informed data Gathering and Analysis Toolkit and Unified REporting System (LIGATURES)

Recent military missions demonstrate the need for understanding the socio-cultural landscape, which requires access to timely and detailed data. Existing approaches to HSCB data collection have proven inadequate and the lack of data has become a key constraint for modeling and analysis efforts. Accordingly, we propose to construct the Language Informed data Gathering and Analysis Toolkit and Unified REporting System (LIGATURES). LIGATURES will combine automated language processing of open-source materials, such as news sites and blogs, with a field data collection tool. The results of the text analysis will suggest topics and trends that can serve as the basis for more finely detailed data collection from the field. We will leverage existing capabilities for both key elements of the project, including an integrated suite of text analytics and a field data collection application designed to run on handheld devices. The combined system will assist analysts in discovering topics of interest from text materials, constructing well-formed questions for field data collection, integrating the two sources of data, and visualizing the results. This approach will allow for enhanced data collection and analysis at multiple levels of temporal and geographic granularity.