Inferring Travel from Social Media Alessio Signorini - - PowerPoint PPT Presentation

▶

inferring travel from social media

Inferring Travel from Social Media Alessio Signorini - - PowerPoint PPT Presentation

Sep 28, 2023 479 likes •791 views

Inferring Travel from Social Media Alessio Signorini <alessio-signorini@uiowa.edu> Alberto Maria Segre <alberto-segre@uiowa.edu> Philip Polgreen <philip-polgreen@uiowa.edu> ONCE UPON A TIME... H1N1 TWEET VOLUME CDC

slide-1

SLIDE 1

Inferring Travel from Social Media

Alessio Signorini <alessio-signorini@uiowa.edu> Alberto Maria Segre <alberto-segre@uiowa.edu> Philip Polgreen <philip-polgreen@uiowa.edu>

slide-2

SLIDE 2

ONCE UPON A TIME...

slide-3

SLIDE 3

slide-4

SLIDE 4

slide-5

SLIDE 5

H1N1 TWEET VOLUME

CDC recommends canceling travels plans Pandemic level raised to 5 Number of confirmed cases reach 1000

slide-6

SLIDE 6

AMERICAN IDOL 2009

LAMBERT ALLEN

vs.

5 10 15 20 25 30 35 40 45

More Positive Tweets about Kris Allen

% positive tweets days

slide-7

SLIDE 7

REAL-TIME ILI% ESTIMATE

09/40 09/41 09/42 09/43 09/44 09/45 09/46 09/47 09/48 09/49 09/50 09/51 09/52 10/01 10/02 10/03 10/04 10/05 10/06 10/07 10/08 10/09 10/10 10/11 10/12 10/13 10/14 10/15 10/16 10/17 10/18 10/19 10/20 0.5 1 1.5 2 2.5 3 3.5 4 4.5 5 5.5 6 6.5 7 7.5 8 8.5

Reported vs. Predicted Weekly ILI%

Flu Season 2009-2010 - United States

% ILI

Predicted Reported

1-fold validation ~ error avg=0.28%, min=0.04%, max=0.93%. Std=0.23%

slide-8

SLIDE 8

DEFINITELY A GOOD IDEA!

slide-9

SLIDE 9

SICK PEOPLE STILL TRAVEL

+

+

CURRENT FLU MAP TRAVEL MODEL

slide-10

SLIDE 10

CENSUS TRAFFIC TICKETS MONEY CELL PHONES

TRAVEL MODELS

slide-11

SLIDE 11

CENSUS TRAFFIC TICKETS MONEY CELL PHONES

TRAVEL MODELS

slide-12

SLIDE 12

CENSUS TRAFFIC TICKETS MONEY CELL PHONES

TRAVEL MODELS

slide-13

SLIDE 13

CENSUS TRAFFIC TICKETS MONEY CELL PHONES

TRAVEL MODELS

slide-14

SLIDE 14

CENSUS TRAFFIC TICKETS MONEY CELL PHONES

TRAVEL MODELS

slide-15

SLIDE 15

CENSUS TRAFFIC TICKETS MONEY CELL PHONES

TRAVEL MODELS

slide-16

SLIDE 16

GPS ADDED TO CELL PHONES

STEVE JOBS

slide-17

SLIDE 17

GPS ADDED TO CELL PHONES

STEVE JOBS

slide-18

SLIDE 18

LOCATION-BASED APPS

slide-19

SLIDE 19

FOCUSING ON THE MOST POPULAR

CHECK-IN TO PLACES TO EARN BADGES TWEETS CAN BE GEO-LOCATED

slide-20

SLIDE 20

FOLLOW PEOPLE EVERYWHERE

RESTAURANT BAR DOCTOR GYM OFFICE STARBUCKS

slide-21

SLIDE 21

DATA COLLECTED

Number of Locations

76 MILLION

Number of Users

6 MILLION

slide-22

SLIDE 22

DATA CLEANUP

CASUAL USERS (<5 locations) TOO FREQUENT (>1 every 5 secs) TOO FAST (>1800 km/h)

slide-23

SLIDE 23

DISTANCE TRAVELLED

0 < 1 mile 1 < 10 miles 10 < 100 miles 100 < 1000 miles 1000 < 10000 miles 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%

50% 85% 97% 99% 100%

% Trips % Cumulative

slide-24

SLIDE 24

TIME INTERVAL

10s 30s 1m 2m 5m 10m 15m 30m 1h 2h 6h 12h 1d 2d 1w 0% 2% 4% 6% 8% 10% 12% 14% 16%

0% 1% 4% 8% 15% 21% 24% 31% 38% 46% 59% 69% 81% 89% 97%

% Trips % Cumulative

slide-25

SLIDE 25

TRIPS vs. DISTANCE

Monday Tuesday Wednesday Thursday Friday Saturday Sunday

16% 16% 11% 14% 14% 17% 12% 19.8 18.5 22.3 20.8 22.0 21.2 21.6

% Trips Miles

slide-26

SLIDE 26

TYPICAL NEW YORK CITY DAY

6 AM 2 PM 8 PM

slide-27

SLIDE 27

TRACKING INDIVIDUALS

slide-28

SLIDE 28

AGGREGATES BETWEEN U.S. STATES

slide-29

SLIDE 29

WHERE TO GET MORE INFORMATION

Alessio Signorini

alessio-signorini@uiowa.edu http://www.cs.uiowa.edu/~asignori/

UIOWA Computational Epidemiology Group

http://compepi.cs.uiowa.edu paper and datasets will be soon available

n the CompEpi website