april 30 & may 1, 2010 storms

29
Apologies for the use of text in this slide show. This was slide deck is intended to provide the findings of a Tweet test performed by the Arkansas Geographic Information Office. 1

Upload: learon-dalby

Post on 31-May-2015

994 views

Category:

Documents


2 download

DESCRIPTION

This was a test of the utility of Twitter during a couple of weather events. The test was performed by the Arkansas Geographic Information Office. The kml can be downloaded from http://bit.ly/bKzf5T

TRANSCRIPT

Page 1: April 30 & May 1, 2010 Storms

1

Apologies for the use of text in this slide show. This was slide deck is intended to provide the

findings of a Tweet test performed by the Arkansas Geographic Information Office.

Page 2: April 30 & May 1, 2010 Storms

2

This was Just a Test

Prepared by: Arkansas Geographic Information Office

www.gis.arkansas.gov

All pictures shown; tweeted with #ArwxA KMZ can be downloaded from

http://bit.ly/bKzf5TStill working on date/time format

Page 3: April 30 & May 1, 2010 Storms

3

#ARwx Tweet TestApril 23-26, 2010

April 29 – May 3, 2010

Prepared by: Arkansas Geographic Information Office

www.gis.arkansas.gov

All pictures shown; tweeted with #ArwxA KMZ can be downloaded from

http://bit.ly/bKzf5TStill working on date/time format

Page 4: April 30 & May 1, 2010 Storms

4

There is a geographic component to TweetsAll tweets were not located properly during this test

Page 5: April 30 & May 1, 2010 Storms

5

There is a geographic component to TweetsLocation is a significant component

Page 6: April 30 & May 1, 2010 Storms

6

Purpose of Test• Determine twitter use for an event• Determine acceptance of a hashtag• Determine acceptance of geoenabled tweets• Figure out if this is useful

http://www.srh.noaa.gov/lzk/?n=svr0410a.htm

Page 7: April 30 & May 1, 2010 Storms

7

Order of events

LR NWS reports strong thunderstorms, and possible tornadoes for the weekend

AGIO implements an API that will capture Tweet information with the hashtag #ARwxAGIO tweets “Pls consider enabling geotagging, and using the #ARwx hashtag”RT by several individuals, ADEM, and Arkansas.gov

Page 8: April 30 & May 1, 2010 Storms

8

Results April 23-26, 2010

• Safe Software Twitter Workbench worked properly– Data was captured and stored in a database– Data can be viewed in GoogleEarth

• Tweets– 32 unique users– 10 geotagged (lat/long)– 77 profile was used to locate– 9 could not be located– 96 total number of tweets during this event

Page 9: April 30 & May 1, 2010 Storms

9

Results April 23-26, 2010

• Safe Software Twitter Workbench worked properly– Data was captured and stored in a database– Data can be viewed in GoogleEarth

• Tweets– 32 unique users– 10 geotagged (lat/long)– 77 profile was used to locate– 9 could not be located– 96 total number of tweets during this event

Yeah!!!

Not a ‘significant’

Event

Page 10: April 30 & May 1, 2010 Storms

10

Information Captured

• Date / Time Created• Tweet ID• Tweet Text• Tweet User• Tweet User Profile Image• Location (lat-long / profile)• Search Text = #arwx• Geometry

Page 11: April 30 & May 1, 2010 Storms

11

Results April 30-May 3, 2010

• Safe Software Twitter Workbench- Failed*– A number of tweets were not captured

• Issues identified:– Number of Twitter API calls per hour– Configuration of scripts

» Each of these are being addressed for next test

• An export from Twapper allowed analysis– Captured Tweets– Georefrenced using profiles captured from failed test– Manually inserted several based on profile

description– Exported to KML*Failure of the workbench was due to implementation; not the Safe Software product

Page 12: April 30 & May 1, 2010 Storms

12

Results April 30-May 3, 2010

• Tweets– 219 unique users– 19 geotagged (lat/long)– 1,425 profile was used to locate– 135 could not be located– 1,579 total number of tweets during this event

• Users– Most tweets by a single user 100– User retweeted the most 108 (@wxmandan – LR

NWS)

Page 13: April 30 & May 1, 2010 Storms

13

Process Used to Generate KML

• Exported #ARwx from Twapper• Performed table join based on userid to the

data captured from the failed test– Inserted location to a number of tweets from

Twapper• Removed duplicates• Attempted to adjust date and time to CST• Ran Safe Software workbench to generate a

kml

Page 14: April 30 & May 1, 2010 Storms

14

General ObservationsApril 30 – May 3, 2010

Page 15: April 30 & May 1, 2010 Storms

15

General ObservationsApril 30 – May 3, 2010

Page 16: April 30 & May 1, 2010 Storms

16

General ObservationsApril 30 – May 3, 2010

Page 17: April 30 & May 1, 2010 Storms

17

General ObservationsApril 30 – May 3, 2010

Event was primarily southeast of this area. Twitter activity corresponds.

Page 18: April 30 & May 1, 2010 Storms

18

General ObservationsApril 30 – May 3, 2010

Tweets increased as event unfolded and decreased as threat subsided.

Page 19: April 30 & May 1, 2010 Storms

19

General ObservationsApril 30 – May 3, 2010

That’s just cool.

Page 20: April 30 & May 1, 2010 Storms

20

General Test Observations• Determine twitter use for an event

– Twitter proved useful for communicating the events as they unfolded. Tweets provided on the ground information and pictures.

• Determine acceptance of a hashtag– The hashtag was generally accepted, but took roughly 18 hours for

uptake• Determine acceptance of geoenabled tweets

– The majority of tweets were not geotagged. Several profiles did not allow for any location information to be identified.

• Figure out if this is useful– No doubt twitter is useful for communicating events. The next step

will be evaluating protocols needed for real-time analysis and bi-directional communication

Page 21: April 30 & May 1, 2010 Storms

21

The power of location

Why test the use?

Page 22: April 30 & May 1, 2010 Storms

22

County Boundaries

Page 23: April 30 & May 1, 2010 Storms

23

Earthquake Intensity

Page 24: April 30 & May 1, 2010 Storms

24

Roads

Page 25: April 30 & May 1, 2010 Storms

25

Bridges

Page 26: April 30 & May 1, 2010 Storms

26

Bridges

For Example:Crowd source damage

assessments following an earthquake

Page 27: April 30 & May 1, 2010 Storms

27

Considerations• Network

– Assumes network access– Assumes Twitter (in this case) is available

• Education– Enabling geotagging

• Acceptance– Geotagging– Ability to provide reports

• Mapability– API works properly– API provides useful information

• Usability

– Filtering the noise• Can the appropriate protocols be put in place to make this a

useful tool for hearing those that ‘call for help’ or submit ‘field reports’?

– The handling of date/time stamps

Page 28: April 30 & May 1, 2010 Storms

28

Summary

The recent events have provided us with good information to use in our test. We will continue to analyze the information and determine how the power of the technology might be further used in future events.

Page 29: April 30 & May 1, 2010 Storms

29

[email protected]: @learondalby

http://www.slideshare.net/learondalby

Special Thanks to @Kirrilian for technical work