4. TWITTER’S FACTS
255 million users active (monthly)
500 million tweets per day
5. TWITTER’S FACTS
255 million users active (monthly)
500 million tweets per day
78% of users are active on mobile devices
6. TWITTER’S FACTS
255 million users active (monthly)
500 million tweets per day
78% of users are active on mobile devices
77% of accounts are outside the U.S.
7. TWITTER’S FACTS
255 million users active (monthly)
500 million tweets per day
78% of users are active on mobile devices
77% of accounts are outside the U.S.
585 gallons (>2000 liters) of coffee per week
12. ANSWER QUESTIONS ABOUT US
How large is the circle of our friends?
The social brain hypothesis:
13. ANSWER QUESTIONS ABOUT US
How large is the circle of our friends?
The social brain hypothesis:
Typical social group size determined by neocortical
size
14. ANSWER QUESTIONS ABOUT US
How large is the circle of our friends?
The social brain hypothesis:
Typical social group size determined by neocortical
size
Measured in various primates, extrapolated for
humans: 100-200 (Dunbar’s Number)
15. VALIDATION OF DUNBAR’S NUMBER IN TWITTER CONVERSATIONS
By using 380 millions @ messages of about 1.7 millions
users, we built the reciprocated weighted network
A) B)
1
Alice
2
Bob
5
Cathy
3
Dan
4
Alice
6
Bob
7
Bob
10
Ellie
9
Cathy
11
Bob
kin
win
wout
A
kin
win
wout
kin
win
wout
B C
E
D
= 2
= 1
= 2
= 1
kout
= 3
= 3
= 4
= 3
kout
= 1
= 1
= 1
= 2
kout
= 1
= 1
= 1
= 1
kin
kout
win
wout
= 0
= 1
= 0
= 1
kin
kout
win
wout
B. Goncalves, N. Perra, A. Vespignani, Modeling Users' Activity on Twitter Networks: Validation of Dunbar's Number, PLoS ONE 6(8), 2011
16. VALIDATION OF DUNBAR’S NUMBER IN TWITTER CONVERSATIONS
0 50 100 150 200 250 300 350 400 450 500 550 600
1 2 3 4 5 6 7 8
tout
kout
A)
50 100 150 200 250 300 350 400 450 500 550 600
0 50 100 150 0 l
B)
!out
i =
P
j !ij
kout
i
Average Weight per Connection
B. Goncalves, N. Perra, A. Vespignani, Modeling Users' Activity on Twitter Networks: Validation of Dunbar's Number, PLoS ONE 6(8), 2011
17. VALIDATION OF DUNBAR’S NUMBER IN TWITTER CONVERSATIONS
Average Weight per ConnectionNumber of connections for which interaction strength is highest
0 50 100 150 200 250 300 350 400 450 500 550 600
1 2 3 4 5 6 7 8
tout
kout
A)
50 100 150 200 250 300 350 400 450 500 550 600
0 50 100 150 0 l
B)
!out
i =
P
j !ij
kout
i
B. Goncalves, N. Perra, A. Vespignani, Modeling Users' Activity on Twitter Networks: Validation of Dunbar's Number, PLoS ONE 6(8), 2011
18. MAPPING THE USE OF LANGUAGES
D. Mocanu, A. Baronchelli, N. Perra, B. Goncalves, A. Vespignani, The Twitter of Babel: Mapping World Languages through Microblogging
Platforms, PLoS ONE, 8(4), 2013
19. MAPPING THE USE OF LANGUAGES
564 days of data collections (Twitter’s gardenhose)
D. Mocanu, A. Baronchelli, N. Perra, B. Goncalves, A. Vespignani, The Twitter of Babel: Mapping World Languages through Microblogging
Platforms, PLoS ONE, 8(4), 2013
20. MAPPING THE USE OF LANGUAGES
564 days of data collections (Twitter’s gardenhose)
~650 K Tweets/day with live GPS
D. Mocanu, A. Baronchelli, N. Perra, B. Goncalves, A. Vespignani, The Twitter of Babel: Mapping World Languages through Microblogging
Platforms, PLoS ONE, 8(4), 2013
21. MAPPING THE USE OF LANGUAGES
564 days of data collections (Twitter’s gardenhose)
~650 K Tweets/day with live GPS
~ 6 M of users
D. Mocanu, A. Baronchelli, N. Perra, B. Goncalves, A. Vespignani, The Twitter of Babel: Mapping World Languages through Microblogging
Platforms, PLoS ONE, 8(4), 2013
22. MAPPING THE USE OF LANGUAGES
564 days of data collections (Twitter’s gardenhose)
~650 K Tweets/day with live GPS
~ 6 M of users
191 countries (110 analyzed)
D. Mocanu, A. Baronchelli, N. Perra, B. Goncalves, A. Vespignani, The Twitter of Babel: Mapping World Languages through Microblogging
Platforms, PLoS ONE, 8(4), 2013
23. MAPPING THE USE OF LANGUAGES
564 days of data collections (Twitter’s gardenhose)
~650 K Tweets/day with live GPS
~ 6 M of users
191 countries (110 analyzed)
Language detected 78 (Using Chromium)
D. Mocanu, A. Baronchelli, N. Perra, B. Goncalves, A. Vespignani, The Twitter of Babel: Mapping World Languages through Microblogging
Platforms, PLoS ONE, 8(4), 2013
24. MAPPING THE USE OF LANGUAGES
D. Mocanu, A. Baronchelli, N. Perra, B. Goncalves, A. Vespignani, The Twitter of Babel: Mapping World Languages through Microblogging
Platforms, PLoS ONE, 8(4), 2013
25. MAPPING THE USE OF LANGUAGES
D. Mocanu, A. Baronchelli, N. Perra, B. Goncalves, A. Vespignani, The Twitter of Babel: Mapping World Languages through Microblogging
Platforms, PLoS ONE, 8(4), 2013
26. MAPPING THE USE OF LANGUAGES
D. Mocanu, A. Baronchelli, N. Perra, B. Goncalves, A. Vespignani, The Twitter of Babel: Mapping World Languages through Microblogging
Platforms, PLoS ONE, 8(4), 2013
27. MAPPING THE USE OF LANGUAGES
D. Mocanu, A. Baronchelli, N. Perra, B. Goncalves, A. Vespignani, The Twitter of Babel: Mapping World Languages through Microblogging
Platforms, PLoS ONE, 8(4), 2013
28. MAPPING THE USE OF LANGUAGES
D. Mocanu, A. Baronchelli, N. Perra, B. Goncalves, A. Vespignani, The Twitter of Babel: Mapping World Languages through Microblogging
Platforms, PLoS ONE, 8(4), 2013
29. MAPPING THE USE OF LANGUAGES
D. Mocanu, A. Baronchelli, N. Perra, B. Goncalves, A. Vespignani, The Twitter of Babel: Mapping World Languages through Microblogging
Platforms, PLoS ONE, 8(4), 2013
40. PREDICT THE SEASONAL FLU
Extracting features of geographical
locations, languages, and key words
from Twitter, Google data, and ILI
trend from CDC data.
Generative models
Calibrating generative models
with multivariate fit.
Stochastic simulations
Inputs
Parameters selection Forecasts
STAGE 1 STAGE 2 STAGE 3
A
A
B
B
C
C E
D
E
D
Twitter data
Google data
Multivariate fit
Analyzing the forcasting results with CDC data in the past
seasons
Forecasting
CDC
42. AND MORE…
Predicting the results of popular votes (American Idol).
F. Ciulla et al, EPJ Data Science, 1, 8, 2012
43. AND MORE…
Predicting the results of popular votes (American Idol).
F. Ciulla et al, EPJ Data Science, 1, 8, 2012
Understanding human communications patterns (work
in progress)
44. AND MORE…
Predicting the results of popular votes (American Idol).
F. Ciulla et al, EPJ Data Science, 1, 8, 2012
Understanding human communications patterns (work
in progress)
Understanding the spreading of # (work in progress)
45. AND MORE…
Predicting the results of popular votes (American Idol).
F. Ciulla et al, EPJ Data Science, 1, 8, 2012
Understanding human communications patterns (work
in progress)
Understanding the spreading of # (work in progress)
Mapping cultural differences (work in progress)