No abstract

Social media create the opportunity for a truly connected world and change the way people communicate, exchange ideas and organize themselves into virtual communities. Both understanding online behavior and processing online content are of strategic importance for security applications. However, high volumes, noisy data and rapid changes of topics impose challenges that hinder the efficacy of classification models and the relevance of semantic models. This paper performs a comparative analysis on supervised, unsupervised and semantic-driven approaches used to analyze social data streams. The goal of the paper is to determine whether empirical findings support the enhancement of decision support and pattern recognition applications. The paper reports on research that has used various approaches to identify hidden patterns in social data collections where text is highly unstructured, comes with a mix of modalities and has potentially incorrect spatial-temporal stamps. The conclusion reports that the disconnected use of machine learning models and semantic-driven approaches in mining social media data has several weaknesses.

No abstract

No abstract

This report summarizes the findings of an exploratory team of the North Atlantic Treaty Organization (NATO) Information Systems Technology panel into ContentBased Analytics (CBA). The team carried out a technical review into the current status of theoretical and practical developments of methods, tools and techniques supporting joint exploitation of multimedia data sources. In particular, content-based information retrieval and analytics was considered as a means to allow military experts to exploit multiple data sources in a rapid fashion for sensemaking and knowledge generation. Elements included contextual understanding of complex events through computational/human processing techniques, event prediction through the automated extraction of network features, temporal trends, hidden clusters and resource flows, and the use of machine processing for automated translation, parsing, information extraction, and summarization of unstructured and semistructured data. The main conclusions of the study are that important research gaps exist in all the technical areas covered in this report. Though the research areas and developments are being advanced in the military sector and the civil sector, in particular, they remain at low levels of technical maturity for defense and security system applications. It is recommended that NATO collaborative research effort be expanded to advance those approaches that are most pertinent to our overall aim of enhancing the contextual understanding of complex events through CBA of heterogeneous multimedia streams.In today's coalition military environment, decisions are needed quickly within a contextual environment that is increasingly uncertain and complex. Current military information systems do not collect sufficient data on local attitudes, culture, and human issues, all of which frame the military decision parameters. Analysis of information tends to be centralized in operational or strategic levels of command, leaving tactical commanders without the ability to maintain awareness of information that is localized and dynamic. Content-based information retrieval and analytics is a means