Loading Events

« All Events

  • This event has passed.

Infection Hot Spot Mining from Social Media Trajectories in Brazilian Cities

February 21, 2018 @ 1:00 pm - 2:00 pm

Infection hot spot mining from social media trajectories
Traditionally, in health surveillance, high-risk zones are identified based only on the residence address or the working place of diseased individuals. This provides little information about the places where people are infected, the truly important information for disease control. The recent availability of spatial data generated by geotagged social media posts offers a unique opportunity: by identifying and following diseased individuals, we obtain a collection of sequential geo-located events, each sequence being issued by a social media user. The sequence of map positions implicitly provides an estimation of the users’ social trajectories as
they drift on the map. The existing data mining techniques for spatial cluster detection fail to address this new setting as they require a single location to each individual under analysis.
We present two stochastic models with their associated algorithms to mine this new type of data. The Visit Model finds the most likely zones that a diseased person visits, while the Infection Model finds the most likely zones where a person gets infected while visiting. We demonstrate the applicability and effectiveness of our proposed models by applying them to more than 100 million geotagged tweets from Brazil in 2015. In particular, we target the identification of infection hot spots associated with dengue, a mosquito-transmitted disease that affects millions of people in Brazil annually, and billions worldwide. We applied our algorithms to data from 11 large cities in Brazil and found infection hotspots, showing the usefulness of our methods for disease surveillance.
Short Bio

Renato Assuncao is a Professor in the Department of Computer Science, Universidade Federal de Minas Gerais (UFMG) located in Belo Horizonte, Brazil.
His research is focused on the development of algorithms and methods of spatial statistical data (data that has geographical coordinates). Most of his work is connected to problems from epidemiology, actuarial risk, and demographic analysis.

Details

Date:
February 21, 2018
Time:
1:00 pm - 2:00 pm
Event Categories:
, ,
Event Tags:
, ,

Venue

802 International Affairs Building
420W 118th Street
New York, NY 10027 United States
+ Google Map
Phone:
212-854-4643
Website:
ilas.columbia.edu