@inbook{dd5892c9a93e40839505c232b8f8e600,
title = "Clustering heterogeneous semi-structured social science datasets for security applications",
abstract = "Social scientists have begun to collect large datasets that are heterogeneous and semi-structured, but the ability to analyze such data has lagged behind its collection. We design a process to map such datasets to a numerical form, apply singular value decomposition clustering, and explore the impact of individual attributes or fields by overlaying visualizations of the clusters. This provides a new path for understanding such datasets, which we illustrate with three real-world examples: the Global Terrorism Database, which records details of every terrorist attack since 1970; a Chicago police dataset, which records details of every drug-related incident over a period of approximately a month; and a dataset describing members of a Hezbollah crime/terror network in the U.S.",
keywords = "Chicago policing, Clustering, Crime, Global terrorism database, Hashing, Hezbollah, Terrorism",
author = "Skillicorn, {D. B.} and C. Leuprecht",
year = "2018",
doi = "10.1007/978-3-319-78021-4_9",
language = "English",
isbn = "9783319780207",
series = "Advanced Sciences and Technologies for Security Applications",
publisher = "Springer",
pages = "181--191",
editor = "Masys, {Anthony J.}",
booktitle = "Security by design",
address = "United States",
}