“Pennsylvania State University – Senseplace and GeoVizToolkit”
VAST 2011 Challenge
Grand Challenge – Cause and
Effect
Authors and
Affiliations (in alphabetical order):
Students:
Ying Chen2 yxc242@ist.psu.edu
Nicklaus
Giacobe2 nxg13@ist.psu.edu
Anuj Jaiswal2 ajaiswal@psu.edu
Wei Luo1 wul132@psu.edu
Alexander Savelyev1 savelyev@psu.edu
Vitalie Victorov2
vwv5007@psu.edu
Sen Xu1
sux100@psu.edu
Faculty &
Staff:
Justine Blanford1 jib18@psu.edu
Frank Hardisty1
hardisty@psu.edu
Alan MacEachren1 macheachren@psu.edu
Prasenjit Mitra2
pmitra@ist.psu.edu
Scott Pezanoski1 spezanowski@psu.edu
Anthony Robinson1 arobinson@psu.edu
1 Department of Geography, The
Pennsylvania State University
2 College of
Information Sciences and Technology, The Pennsylvania State University
Tool(s):
Our
project makes use of a variety of different tools that allow us to collate and
visualize the information. ArcGIS 10 (by Environmental Systems Research Institute
(ESRI))
is a fully developed Geographic Information System (GIS) that allows for the
integration and visualization of spatial data.
Scripts to further mine the data were developed in Java. These scripts were used to compare articles,
extract entities and georeference locations mentioned
in news articles. Although ArcGIS has
the ability to create graphs to illustrate frequency, Microsoft Excel was used
to summarize symptom counts using the graphing tools as well as create the
timelines. One of the timelines illustrated was created using Excel Timeline
Template developed by Vertex42. In addition the SensePlace2 tool
developed at the GeoVISTA
Center
was used to perform additional pattern analysis of the microblog
data. In addition open-source software such as ANNIE and OpenCalais
were used to perform entity extraction on the documents. We wrote code in Java to geo-code the
extracted location names and used Excel to store the metadata associated with
each text document. Lucene
was used to index the text and enable keyword search and NodeXL,
a tool built by the Schneiderman group to display and
analyze network entity-relationships.
Video:
Are
any terrorist activities related to the current epidemic?
We considered two
possibilities of terrorist attacks:
1.
The chemical truck that hit the food truck to create a spill
in the river. Instead of the driver
falling asleep, this was a planned attack.
There could be two options.
First, the driver of the chemical truck took part in a “suicide
attack”. The second is that there was a
monitoring device in the chemical truck that resulted in an explosion even
before the truck collided and that caused the truck to hit the other food
truck. The truck may have been monitored
and the explosion set off but this is unlikely that the first explosion would
not be detected and could be timed so well.
We lean towards calling this a suicide attack. The other evidence that we list below point
towards it being a terrorist attack.
2.
The convention center was emptied using a fake fire
call. It is possible that some germs
could have been sprayed in several parts of the center when people evacuated by
some miscreants. However, doing so
successfully and infecting a large population in a short time is highly
unlikely and would have been caught by closed-circuit cameras, etc.
Describe
the series of events, planned or otherwise, that led to the current epidemic.
The series of events that took place are as follows. There was some death of animals but we do not
have information about what caused it.
Then, the trucking company was intruded.
We posit that this was done to obtain (a) information about the truck
routes and manifests, alter the cargo being carried by trucks, alter the
records to enable the terrorists to ship explosives and chemicals and
bio-hazards, and/or (b) edit the employment records to add a new
employee/driver (obtained from Mini Challenge 2). About a month later, the truck accident
spilled bio-hazards onto the river. The
water-supply and the fish got polluted.
People drinking the water and/or consuming the fish got sick (obtained
from Mini Challenge 3). The tweets
confirm the sickness of people and the hospitals are treating a lot of people
for that sickness (obtained
from Mini Challenge 1).