This article is a seminal piece and a foundational resource in the field of social media analytics and open source intelligence by some of the field’s leading authors.
This 2013 article focuses on Natural Language Processing (NLP) and particularly social media monitoring of Twitter for purposes of national security. The authors conduct a literature review of five recent social media monitoring systems in the security domain, briefly present and discuss the merits of each system, and highlight a gap in current sentiment analysis capabilities. The authors then present their own system, the EMOTIVE system, a project jointly funded by the United Kingdom-based Defense Science and Technology Laboratory (DSTL) and EPSRC, which focuses on monitoring fine-grained emotional responses relating to events of importance to national security. The authors contend that while social media has become a valid, valuable and effective real-time tool for gauging public subjective reactions to events and entities, the nature of “big-data” use for gauging public reactions has automated the process, and made human and expert monitoring largely unfeasible.
This article will be of particular use to researchers, practitioners and policy makers interested in social media monitoring for purposes of national security. Social media streams such as Twitter have become a vast source of daily real-time data, covering every range of human communication. Within this rich resource of information sharing, users express serious reactions to events, issues and trending topics. Publically visible events now “break news” over social media streams first, and only then get picked up and followed by mainstream media. By presenting the background considerations for social media monitoring, reviewing recent systems, and describing a compilation of essential features expected from most national security monitoring systems, the authors have made this a foundational and informative piece for the PVE community.