MOSAIC: Modeling the Spread of Attitudes and Information in Cultural Data

The attitudes and opinions of populations around the world are reflected in the content they create on the internet. In counter-insurgency (COIN) and related operations, it is critically important to understand the attitudes of different populations, but it remains very hard to get timely, detailed data relevant to strategic metrics. Online data has been vastly underutilized due to the sheer amount of data and its unstructured nature. To address this problem, Aptima proposes development of MOSAIC (MOdeling the Spread of Attitude and Information in Cultural data). MOSAIC will leverage Aptima"s LaVA language processing technology to extract high-level concepts from electronic media, such as online news, blogs, and social media. In addition, our partners, SentiMetrix, Inc., will apply their technologies to extract entities and sentiment from the same data. These entities, sentiment, and concepts will be combined to derive"memes,"or units of cultural information about the attitudes and opinions present in the data. Finally, we will apply epidemiologically-inspired models of information diffusion to these memes to better understand their temporal and spatial change and spread. From these models we can derive a set of strategic metrics related to the changing attitudes of the population.