Cultural Dimensions in Twitter: Time, Individualism and Power

Ruth García-Gavilanes (UPF - Barcelona) Daniele Quercia (Yahoo! Barcelona) Alejandro Jaimes (Yahoo! Barcelona)

1

Culture

2

Microblogs

3

WHAT IS CULTURE ?

4

CULTURE

Culture is a dimension that distinguishes members of one group or category of

people from others

5

6

7

HOW TO MEASURE CULTURE • Geert Hofstede: Cultural dimensions

Individualism Power Distance

•  Levine : Pace of Life (Geography of time) •  Perception of time

• Edward T. Hall

Monochronic vs Polychronic

8

Pace of Life

Individualism Power Distance

9

Not considered Levine

Hall

Culture and Social Media

Can such differences also be captured from online interactions?

10

How to measure culture online? • Pace of Life

Predictability (tweets, mentions) Tweets in working hours

•  Individualism vs. Collectivism Users interacting with others (mentions)

• Power Distance : Popularity Follow, recommend and accept recommendation preferentially from more popular users (in-degree imbalance).

11

Sampling for 10 weeks in 2011

12

2.34 geolocated

users

follows

#FollowFridday

12.6 K 1.9M

362 K 100>= out-degree <=1000

Top 30 countries to study The top 30 countries by # of users is representative of internet users

13

United States

Brazil

United KingdomIndonesia

Canada

Mexico JapanNetherlandsVenezuela SpainAustralia

Germany

FranceArgentinaChileSouth Korea

ColombiaIrelandSouth Africa IndiaPhilippines TurkeyItalyRussiaSweden

New ZealandNorwayMalaysiaBelgiumSingapore

4

5

6.5 7.0 7.5 8.0 8.5Log(Internet Penetration)

Log(

User

Cou

nt)

r = 0.63***

RESULTS

14

Pace of Life : Predictability Entropy

a) tweets b) mentions

− pi ( j)log2 pi ( j)j=1

Ni

∑pi ( j) :

15

12AM

6AM

9AM

6 PM

9PM

12PM

# tweets in working hours

Interval j

Pace of Life : Predictability

Tweets Mentions

Users in working hours

Pace of life **-0.62 **-0.68 **-0.58

16

The higher the pace of life , the more predictability The higher the pace of life the less fraction of users will tweet during working hours

p < 0:005 (***), p < 0:05 (**), and p < 0.1 (*)

Individualism : Interacting with others

IndonesiaVenezuela

MexicoJapanBrazilColombia

ChileSouth Korea Argentina

PhilippinesMalaysia Spain NetherlandsTurkeySouth Africa

Singapore Ireland Canada

FranceBelgiumSwedenNorway

New Zealand

Italy

Russia India

Germany

80

85

90

95

100

20 40 60 80

Individualism Index

Fractio

n of E

ngag

emen

t

17

r= ***-0.55

p < 0:005 (***), p < 0:05 (**), and p < 0.1 (*)

Collectivist countries interact more with others

Individualism : Interacting with others

IndonesiaVenezuela

MexicoJapanBrazilColombia

ChileSouth Korea Argentina

PhilippinesMalaysia Spain NetherlandsTurkeySouth Africa

Singapore Ireland Canada

FranceBelgiumSwedenNorway

New Zealand

Italy

Russia India

Germany

80

85

90

95

100

20 40 60 80

Individualism Index

Frac

tion

of E

ngag

emen

t18

Hong et al.. “Language matters in twitter: A large scale study” ICWSM 11

Collectivism Interacting with others

19

Power Distance: popularity imbalance

20

follows

#FollowFridday

Popularity imbalance for:

seed followees

followees recommended

accepted recommended seed

Power Distance: popularity imbalance

Followers Followers/Followees

Users and followees **-0.62 **-0.67 Users and recommended user **-0.56 **-0.46 User and accepted recommended user

-0.44 -0.29

21

p < 0:005 (***), p < 0:05 (**), and p < 0.1 (*)

Users prefer to follow and recommend more popular users than themselves in countries with a higher power distance

Power Indonesia

Venezuela

Norway

MalaysiaSingapore

Chile MexicoPhilippinesColombia

United States South Korea IndiaBrazilCanadaArgentinaAustralia RussiaItalyNew Zealand SpainGermany Japan FranceSouth AfricaUnited KingdomIreland TurkeyNetherlands BelgiumSweden

-1000

0

1000

2000

3000

4000

5000

30 60 90

Power Distance Index

In-de

gree I

mbala

nce

22

Power Indonesia

Venezuela

Norway

MalaysiaSingapore

Chile MexicoPhilippinesColombia

United States South Korea IndiaBrazilCanadaArgentinaAustralia RussiaItalyNew Zealand SpainGermany Japan FranceSouth AfricaUnited KingdomIreland TurkeyNetherlands BelgiumSweden

-1000

0

1000

2000

3000

4000

5000

30 60 90

Power Distance Index

In-de

gree I

mbala

nce

23

27% of all blog trends are about artists and celebrities (Silang et al, 2011)

Why is this important?

Indicator Pace of Time : Predictibility

Individualism:

Mentions

Power Distance:

Imbalance Mentions Users (%) GDP per capita

***0.55 **-0.57 **-0.41 **-0.48

Education ***0.58 **-0.51 -0.24 ***-0.60 Inequality ***-0.53 **0.49 *0.39 ***0.58

24

What is next?

25

•  Language dependent features

•  More Cultural Dimensions

•  Temporal comparisons

More features

What is next?

26

•  User recommender •  Individualistic vs. collectivistic ? •  Predictable vs. unpredictable ?

•  Interfaces personalization •  Do collectivist countries need additional features to

interact easier? •  More engagement?

•  Information Propagation •  By knowing the cultural characteristics of users, can

we increase re-tweet chance?

Application

Thank you @ruthygarcia

27