"Predictive Analytics" is the use of statistical techniques to analyze current and historical facts to predict future events of interest. Predictive analytics uses datasets (and sometimes what is called “big data”) to create models out of historical information by highlighting patterns and correlations and projecting those observations forward with degrees of statistical confidence.
"Data Mining" is an interdisciplinary subfield of computer science. It is the analytical computational process of discovering patterns within these datasets or "big data", and involves methods at the intersection of artificial intelligence, machine learning, statistics, and database systems.
These methods have been applied in the past by statisticians to make predictions about business decisions, politics, public policy (most notably public health), and crime rates.
The application of predictive analytics and data mining for counterterrorism is a relatively new idea. With the explosion of social media in the past ten years, some have observed that social life is now measurable and recordable in a way that it has never been. As such, there is a growing body of literature and practice applying statistical methods to social media data to study social phenomena related to terrorism such as radicalization.
This 2013 article analyzes content generated on Twitter during the attacks at the Boston Marathon in April 2013. The authors perform an in-depth characterization of what factors influenced malicious content and profiles becoming viral.
This paper looks at how data is created and by whom. A particular focus is the intersection between the application programming interface (API) as well as tools used to process data.
This 2012 article focuses on predictive analytics and in particular crime prediction using events and data extracted from Twitter posts. The authors present a preliminary investigation of Twitter-based criminal incident prediction.
This article is based on a research project conducted by the SecDev Group in collaboration with the U.S. National Institute for Justice (NIJ) in San Diego.
This survey reviews the literature and concepts of the data mining of social networks, with special emphasis on their representation as a graph structure. The article is divided into two principal parts:
This article attempts to address the challenge of surveilling potential lone-wolf terrorists. Since these individuals act on their own, information cannot be collected using traditional police methods such as infiltration or wiretapping. Cohen et al.
This paper presents a theoretical computerized system to detect social polarization and to estimate the related chances of violent radicalization. Existing technologies are analyzed to determine how they can be integrated into the proposed system to fulfil the authors’ objectives.
This paper investigates the possibility of forecasting spikes in social tension – defined by the UK police service as “any incident that would tend to show that the normal relationship between individuals or groups has seriously deteriorated” – through social media.
The Ethical Decision-Making and Internet Research document is described as a set of guidelines concerning the day-to-day practices of researchers across multiple disciplines, countries and contexts.
This article addresses the degree to which geolocation prediction is vital to geospatial applications like localised search and local event detection.
This resource contains the description and data analysis from a research project conducted by Fifth Tribe into ISIS’s use of Twitter in the aftermath of the 2015 Paris Attacks.
This resource is an informative, visual and descriptive infographic by Fifth Tribe focused in ISIS’s use of Twitter. The infographic and descriptions in the article were written following the Paris attacks in November 2015.
This article focuses on Data Mining and Social Network Analysis (SNA) amongst bloggers, and in particular the mining of racist groups and cyber hate communities in online blogging websites.
This explanatory thesis is concerned with user generated text, audio and video media. According to Tsagkias two aspects, the social and user generated content, led to the development of two main research branches in social media analysis.
This article concerns whether social media is a valid indicator of political behavior. As the authors discuss, there is considerable debate about the validity of data extracted from social media for studying offline behavior.
This paper sets out to interpolate and predict state-level polling at the daily level by employing a dataset of over 500GB of political tweets from the final months of the 2012 presidential campaign.
The authors of this 2011 article hypothesize that the results of Google Trends, given its daily and weekly reports on queries related to various industries may be correlated to the current level of economic activity in these industries.
This is a foundational report and a seminal work in the study of social media intelligence and open source research. The paper reviews 245 papers in a semi-systematic literature review of how information and insight can be drawn from open social media sources.
This article reveals just how vital geographical location is to geospatial applications like local search and event detection. In this paper, the research team investigates and seeks to improve on the task of text-based geolocation prediction of Twitter users.
This 2014 article uses a case study method to examine the implications of using the emerging technology of predictive analytics in a homeland security context, to provide increased intelligence for counterterrorism initiatives.
This 2013 article examines the case of a Marine Corps reservist who perpetrated a series of attacks against military facilities in Virginia in October and November 2010.
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 recorded talk with Susan Benesch, a fellow at Harvard’s Berkman Center for Internet & Society deals with data driven methods to decrease hate online.
This 2013 book aims to inform government decision-makers, security analysts, and activists on how to use the social world to improve security locally, nationally, globally, and cost-effectively.
This 2014 eBook by some of the field’s leading authors provides a foundational background into social media research and analytics.
This white paper addresses the role of the UK government, social media companies and Internet service providers (ISPs) in monitoring and policing the Internet for extremist and/or terrorism related content.
This paper evaluates two tools for the automated identification of demographic and occupational data from the profile descriptions of Twitter users in the United Kingdom.
+1-613-755-4007 • info@secdev.foundation
Copyright © 2014 - 2017 • The SecDev Foundation
