Smarter Urban Dynamics - SaferCity


SaferCity: a System for Detecting and Analyzing Incidents from Social Media


Michele Berlingerio, Francesco Calabrese, Giusy Di Lorenzo, Xiaowen Dong, Yiannis Gkoufas, Dimitrios Mavroeidis
IBM Research, Dublin, Ireland



SaferCity is a system to identify and analyze public safety related incidents from social media. In contrast to the relevant public safety analytics systems, SaferCity takes into account both official crime and safety issue reports, and uses the two to build a new kind of situational awareness that complements the current view available to law enforcement entities. On one hand, in fact, current commercial systems used by police and other security forces rely mostly on official reports and deployed sensors such as CCTV cameras, audio sensors, emergency calls, and so on. On the other hand, in the last few years, research studies attempted to capture signals of safety issues by extracting knowledge from Social Media, a voluntary but indirect form for reporting safety issues in urban contexts.
SaferCity is based on a new spatio-temporal clustering algorithm that is able to identify and characterize relevant incidents given even a small number of social media reports. We have developed a web-based application exposing the features of the system, and demonstrated its usefulness in detecting, from Twitter, public safety related incidents occurred in New York City, Ireland and Kenya.

Video presentation of Safercity

Clik here.


SaferCity: a System for Detecting Incidents from Social Media, Y Gkoufas, X Dong, M Berlingerio, G Di Lorenzo, F Calabrese, D MavroeidisIEEE International Conference on Data Mining, 2013
Multiscale Event Detection in Social MediaXiaowen Dong, Dimitrios Mavroeidis, Francesco Calabrese, Pascal Frossard, Data Mining and Knowledge Discovery, 2015