<div dir="ltr"><div><div><div>All,<br><br>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 <a href="http://www.sciencedirect.com/science/article/pii/S0167923614000268">recent work</a> 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.<br>
<br></div><div>Now of course, all of this could be used for malicious purposes, just like every other technology in the history of Man.<br><br></div>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.<br>
</div><br></div>Matt<br></div><div class="gmail_extra"><br><br><div class="gmail_quote">On Mon, Apr 21, 2014 at 11:34 AM, Matthew Gerber <span dir="ltr"><<a href="mailto:gerber.matthew@gmail.com" target="_blank">gerber.matthew@gmail.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div><div>Hello,<br><br></div>A new research position has opened within our lab, and we are seeking M.S., Ph.D., and post-doc researchers.<br>
<br></div>One-sentence summary: We are mining social media for indicators of individual routine activities for the purpose of improved crime prediction.<br>
<br>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 <a href="http://ptl.sys.virginia.edu/ptl/projects/asymmetric-threat-prediction" target="_blank">Asymmetric Threat</a>
project); however, these basic questions remain unanswered, leaving a
substantial gap in our understanding of attack processes and their
relationships with individuals’ routine activities.<br><div><div><div><div><div><br>More information can be found <a href="http://ptl.sys.virginia.edu/ptl/projects/routine-activities-analysis-for-crime-prediction" target="_blank">here</a>.<br>
<br></div><div>Sincerely,<br><br><div dir="ltr"><div>Matthew S. Gerber, Ph.D.<br></div><span>Research</span> <span>Assistant</span> <span>Professor</span><br>Department of Systems and Information Engineering<br>University of Virginia</div>
<br></div></div></div></div></div></div>
</blockquote></div><br></div>