[Corpora-List] Open Research Position (M.S. / Ph.D. / post-doc): Analyzing Routine Activities for Crime Prediction

Matthew Gerber gerber.matthew at gmail.com
Fri Apr 25 03:45:16 CEST 2014


Thanks for an interesting discussion following the original post. As expected, the focus turned immediately to the identification of criminals and the civil rights issues associated with automated targeting. This is a natural, though myopic, reaction. My recent work<http://www.sciencedirect.com/science/article/pii/S0167923614000268>and experience in this area suggest that criminals don't often tweet (gangs are a notable exception that I have yet to look into). I am not expecting to find them in the proposed data/project. Modeling individual activity patterns is a means for characterizing geographic spaces in other ways. Do many people in a neighborhood leave for the day to work? If so, that's probably a good place to watch for robberies. Do many people in a neighborhood arrive home late at night? If so, that's probably a good place to watch for assaults/muggings. I've provided victim-based examples because I hypothesize that they're the right place to look given the fact that criminals don't tweet, and if they do they're probably not going to broadcast their criminal intents. Non-criminal intents (e.g., leaving for work) can be just as helpful when it comes to analyzing crime, and they are certainly more plentiful in Twitter data.

Now of course, all of this could be used for malicious purposes, just like every other technology in the history of Man.

To answer some other questions: Yes, I've seen Minority Report. No, it did not inspire this research. No, you're not going to be added to a no-fly list by the fruits of this work. As for a fair trial, that will depend on your country of residence.


On Mon, Apr 21, 2014 at 11:34 AM, Matthew Gerber <gerber.matthew at gmail.com>wrote:

> Hello,
> A new research position has opened within our lab, and we are seeking
> M.S., Ph.D., and post-doc researchers.
> One-sentence summary: We are mining social media for indicators of
> individual routine activities for the purpose of improved crime prediction.
> Longer summary: This project focuses on the spatiotemporal prediction of
> localized attacks carried out against individuals in urban areas. We view
> an attack as the outcome of a point process governed by the interaction of
> attackers, targets, and the physical environment. Our ultimate goal is to
> predict future outcomes of this process in order to increase the security
> of human populations and U.S. assets and interests. However, achieving this
> goal requires a deeper understanding of how attack outcomes correlate with
> the routine activities of individuals in an area. The proposed research
> will generate this understanding and in doing so will answer questions such
> as the following: What are the dimensions along which individuals’
> activities should be quantified for the purpose of attack prediction? How
> can measurements along these dimensions be taken automatically and with
> minimal expense (e.g., via social media)? What are the implications of such
> measurements for attack prediction performance? Subsuming these questions
> is the issue of geographic variation: do our answers change when moving
> from a major U.S. city to a major U.K. city? There has been plenty of
> previous work on spatiotemporal attack prediction (see our Asymmetric
> Threat<http://ptl.sys.virginia.edu/ptl/projects/asymmetric-threat-prediction>project); however, these basic questions remain unanswered, leaving a
> substantial gap in our understanding of attack processes and their
> relationships with individuals’ routine activities.
> More information can be found here<http://ptl.sys.virginia.edu/ptl/projects/routine-activities-analysis-for-crime-prediction>
> .
> Sincerely,
> Matthew S. Gerber, Ph.D.
> Research Assistant Professor
> Department of Systems and Information Engineering
> University of Virginia
-------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 4515 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20140424/0d63de82/attachment.txt>

More information about the Corpora mailing list