Crime analysts often use an area’s historical record to visualize past crimes (e.g., using hot-spot mapping) and predict locations of future criminal activity. These tasks rarely take advantage of the vast repository of unstructured text that is freely available through, for example, news and social media outlets. Such information sources contain detailed descriptions of past, present, and future events, and recent work has shown that these descriptions can improve crime prediction performance. Despite this encouraging result, textual information remains largely unexploited due to its vast size and unstructured format. This special issue of Security Informatics will focus on leveraging text processing techniques (e.g., extraction of events, facts, locations, times, sentiment, etc.) for crime analysis and predictive policing.

We welcome the submission of high-quality, original research on the following topics (within in the context of crime analysis and predictive policing):

* Extraction and geocoding (address resolution) of event locations from unstructured text
* Extraction and normalization of event times from unstructured text
* Extraction of person/group names and sentiment from unstructured text
* Extraction of other useful information from unstructured text
* Processing of “noisy” sources of unstructured text (e.g., Twitter and weblogs)
* Fusion of the above (or other) textual information with criminal incident data

This CFP supersedes a previous, similar one. Please refer to the submission deadlines in this CFP.

Please see the supplied URL for the official CFP, including submission schedule and instructions.