The document discusses a presentation from the Agile 2016 Conference on using georeferenced tweets for identifying disaster-affected areas, specifically during a flood event in Sardinia in November 2013. It outlines methods of data preprocessing, clustering techniques, and visual analysis to assess the spatio-temporal footprint of the disaster, emphasizing the integration of data mining and visual analytics. The conclusions highlight the initial steps towards defining the geospatial impact of floods through social media, with suggestions for further evaluation and improvements.

1. AGILE 2016 Conference, Helsinki - 15th June 2016
Identification of disaster-affected areas using
exploratory visual analysis of georeferenced Tweets:
application to a flood event
V. Cerutti1, G. Fuchs2, G. Andrienko2, N. Andrienko2, F.Ostermann1
1 ITC Faculty of Geo-Information Science and Earth Observation, University of Twente, The Netherlands
2 Fraunhofer IAIS, Sankt Augustin, Germany

2. IN THIS PRESENTATION:
INTRODUCTION METHODS CASE STUDY CONCLUSIONS AND
FUTURE WORK
AKNOWLEDGMENT
1. 2. 3. 4. 5.

3. 1. INTRODUCTION
3

4. 4
RESEARCH CONTEXT AND MOTIVATION
Social media for Disaster Management - Disaster response phase
Enable decision makers in rapid assessment of the situation
Geographic and temporal extent of disaster effects

5. 5
RESEARCH OBJECTIVES
Conceptual management of crisis information
Geospatial footprint of disaster
Situational awareness and decision making

6. Combination of data mining and visual analysis
Detection of areas affected by a disaster
Twitter as data source
6
CASE STUDY OBJECTIVE
Help decision makers to assess the spatio-temporal footprint
of a disaster

7. 2. METHODS
7

8. 8
Tweets pre-processing:
• removal of geographically
unrelated data
• pattern-based removal of
machine-generated data
• natural language processing
to mine the data and classify
and annotate its content
DATA PREPROCESSING

9. CLUSTERING + VISUAL ANALYSIS
9
Clustering techniques to understand how affected places are represented
Tight integration between
computational and visualization
functionality
V-Analytics toolkit (http://geoanalytics.net/)
Need parameterization
 space-time cube
 frequency histograms
 time graphs
 qualitative colouring
 animated maps
 Density-based clustering
 Distance-bounded spatio-temporal event
clustering
 Data-driven territory tessellation
Visual analysis techniques

10. 3. CASE STUDY
10

11. 11
DATA DESCRIPTION AND PREPARATION
Case study: Sardinia flood, 18-19 November 2013
Original dataset: georeferenced Tweets (Dec 2012 -
Apr 2014), bounding box: Italy, collected from
Twitter streaming API
Query: Lexicon of flood-related keywords in Italian
language
Demographic data to normalize the results
Ground truth information from official reports
Final dataset: 3,000 Tweets (Nov 2013)
897 Tweets (18-20 Nov 2013)

12. 12
DATA ANALYSIS
18-19 Nov 2013
Random sample (5%) of georeferenced Tweets
generated during the month of November 2013
Impossible to detect
the flood event
After keyword-based filtering:

13. 13
Spatio-temporal density-based clustering (OPTICS) + visual analysis to select
optimal parameters
DATA ANALYSIS

14. 14
Distance-bounded event clustering + visual analysis to select optimal parameters
DATA ANALYSIS

15. 15
Data-driven territory tessellation + time series of Tweets frequency
DATA ANALYSIS

16. 16
Spatio-temporal density-
based clustering (OPTICS)
Distance-bounded
event clustering
Data-driven territory
tessellation
DATA ANALYSIS

17. 17
RESULTS COMPARISON AND EVALUATION
False negative
Ground truth data Combination of
clustering results
False positive

18. 4. CONCLUSIONS AND
FUTURE WORK
18

19. 19
CONCLUSIONS
 First steps towards an approach to define the geospatial footprint of a
flood event using georeferenced Tweets
 Data mining techniques + exploratory visual analysis of georeferenced
Tweets to identify the areas affected by a flood
 Intuitive and fast procedure
 User evaluation needed
 False positive and false negative need to be addressed
 Further analysis required to obtain more precise footprints

20. 20
Extraction of locations (and other potentially useful information)
mentioned in social media
Comparison locations of origin (geotag) and content
Contextualization and validation of social media information with
authoritative data
FUTURE WORK
Conceptualization of disasters
Content analysis
Geospatial footprint in near real time

21. 5. AKNOWLEDGEMENT
21

22. AKNOWLEDGEMENT
22
COST ACTION IC 1203
• STSM Grant
Fraunhofer Institute for Intelligent
Analysis and Information Systems
• Knowledge
• Software
• Dataset

23. THANKS FOR YOUR ATTENTION
QUESTIONS?
v.cerutti@utwente.nl