USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

65
User Behavior in Microblogs with a Cultural Emphasis Ruth García-Gavilanes Advisor : Ricardo Baeza-Yates Web Research Group Universitat Pompeu Fabra & Yahoo Labs PhD Thesis Defense February 26, 2015

Transcript of USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Page 1: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

User Behavior in Microblogs with a Cultural Emphasis

Ruth García-Gavilanes

Advisor : Ricardo Baeza-YatesWeb Research Group

Universitat Pompeu Fabra& Yahoo Labs

PhD Thesis Defense February 26, 2015

Page 2: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

2

•  The study of the trails left behind by users when they use the web: Interactions, choices, searches, purchases, etc.

•  User interactions are increasingly mediated and shaped by algorithms and computational methods.

•  Massive amount of data

•  Great cultural value

User Behavior

•  Rise of Computational Social Sciences

Introduction

Page 3: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

CSS AGENDA

PRESENT

FUTURE

Develop new instruments to tap into the potential of found data and crowds ‘: building a telescope for the Social Sciences

Online impacts offline! Build new algorithms and tools to shift the current configurations of societies towards better futures.

3Introduction

Claudia Wagner

Page 4: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Social Science Research

Computer Science and Information

Science

Survey Design and Methodology

Objective of CSS

4

Computational Social Science

Introduction

Page 5: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

5

User behavior

Microblogs Culture•  All users: human

recommendations, behavior evolution

•  Cross-country comparisons

Cultural Emphasis

Introduction

Page 6: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

6

Friendship links in Twitter do not need to be reciprocal

I follow you

information

Case Study : Twitter

Introduction

#HASHTAGS

@Mentions & Retweets

Page 7: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

7

#Disasters Teheran, Iran

Introduction

Page 8: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

8Introduction

Background

Kwak et al. What is Twitter, a Social Network or a News Media? WWW’10

Cha et al. Measuring User Influence in Twitter: The Million Follower Fallacy. ICWSM’10

Bakshy et al. Everyone’s an Influencer: Quantifying influence on Twitter. WSDM’11

De Choudhury et al. How Does the Data Sampling Strategy Impact the Discovery of Information Difussion in Social Media? ICWSM’10.

Page 9: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

9Introduction

Goals

•  Study the effect of recommendations made by users

•  Compare the evolution of user behavior through time

•  Find differences and similarities across countries

•  Study how cultural models can be used with data

•  Use cultural models socio economic indicators to study user behavior

In Microblogs :

Page 10: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Contributions•  Providing a study of human generated recommendation on Twitter and its effect.

o  García-Gavilanes et al. Follow My Friends This Friday! An Analysis of Human-generated Friendship Recommendations. SocInfo’13 [Best paper award]

•  Describing the evolution of user behavior over time regarding the content they generate.o  García-Gavilanes et al. Who are my Audiences? A Study of the Evolution of Target Audiences in

Microblogs. SocInfo’14

•  Describing differences and similarities of users across countries regarding the way people tweet and connect with others. o  García-Gavilanes et al. Microblogging without Borders: Differences and Similarities. Websci’11. o  w/ Poblete et al. Do All Birds Tweet the Same? Characterizing Twitter Around the World. In CIKM’11

•  Proposing how to combine anthropological studies of culture with large scale data. •  Correlating how and when people tweet with dimensions of national culture and pace

of life o  García-Gavilanes et al. Cultural Dimensions in Twitter: Time, Individualism and Power. ICWSM’13

[Honorable mention]

•  Improving the prediction of the communication strength between users from different countries by taking into account several cultural and socio-economic indicators taken from diverse sources. o  García-Gavilanes et al. Twitter ain’t Without Frontiers: Economic, Social, and Cultural Boundaries in

International Communication. CSCW’14.

10Introduction

Page 11: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

11

Data Mining Cultural

All users

Q1) What is the effect on users from

Human generated recommendations?

Q2) How do user behavior evolve over time?

Cross-countryQ3) Do all users from

different countries tweet the same?

Q5) Does culture influences the way we

tweet online?

Q6) Can culture influence online interactions with

users from other nations?

Thesis Structure

Q4) What cultural models to use?

Introduction

Page 12: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

12

Data Mining Cultural

All users

Q1) What is the effect on users from

Human generated recommendations?

Q2) How do user behavior

evolve over time?

Cross-countryQ3) Do all users from

different countries tweet the same?

Q5) Does culture influences the way we

tweet online?

Q6) Can culture influence online interactions with

users from other nations?

Thesis Structure

Q4) What cultural models to use?

Introduction

Page 13: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Q1) Human Recommendations

Recommendations 13

[Garcia-Gavilanes et al. Follow My Friends This Friday!, SocInfo’13]

Friendship Recommendations

•  Self organized•  Trendy•  Measurable

Track recommendations during 24 weeks

Page 14: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Q1) Acceptance

Recommendations 14

TotalRecommendation Instances 59,055,205

Accepted Recommendation Instances

354,687

Social link recommendations made by current friends have a measurable effect on

link formation

0.60% instance acceptance

Receiver Recommender Recommendation Week

[Garcia-Gavilanes et al. Follow My Friends This Friday!, SocInfo’13]

4M users

Page 15: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Recommendations 15

Follow Friday recommendations outperform the two alternativeconditions.

Q1) Acceptance

The accepted recommendations have more longevity than other links.

[Garcia-Gavilanes et al. Follow My Friends This Friday!, SocInfo’13]

Page 16: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Q1) Results

Recommendations 16

Features MAPAll 0.496User-based 0.074Relation-based 0.398Recommendation-based 0.062User + Relation 0.518User + Format 0.079Relation + Format 0.379

USER-BASED (per user)•  Attention•  Activity

RELATION-BASED (per pair)•  Tie Strength•  Similarity

RECOMMENDATION-BASED (per recommendation)•  Repetitions•  Format

The link formation is influenced mostly by the user and relation-based characteristics

Rotation Forest

140features

[Garcia-Gavilanes et al. Follow My Friends This Friday!, SocInfo’13]

Page 17: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

17

Data Mining Cultural

All users

Q1) What is the effect on users from

Human generated recommendations?

Q2) How do user behavior evolve over time?

Q4) What cultural models to use?

Cross-countryQ3) Do all users from

different countries tweet the same?

Q4) Does culture influences the way we tweet online?

Q5) Can culture influence online interactions with users from other

nations?

Thesis Structure

Evolution

Page 18: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Active in 2011 & 2013

2011 2013

Users 1,315,313 1,125,968

English Tweets

406,719,999 256,330,241

Min 1 and max 22 tweet per working day.

8M

4.3M

770K

1.1M2011

2013

2011 2013

Q2) DATA

18

Inactive < 1 tweet per dayHyperactive > 22 per day

530K 570K

1.3M

[García-Gavilanes et al. Evolution of Target Audiences. SocInfo’14]

Evolution

Page 19: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Q2)Tweeting Behavior

19

No Mentions

Tweets

With links

Original tweets (OT)

Without links

Mentions

Re-tweets (RT)

No Mentions

With links Without links

Mentions

% % % % % % 2011

% % % % % % 2013

Evolution

[García-Gavilanes et al. Evolution of Target Audiences. SocInfo’14]

Page 20: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Q2) Clusters

20

0%

25%

50%

75%

100%

0%

25%

50%

75%

100%

0%

25%

50%

75%

100%

0%

25%

50%

75%

100%

0%

25%

50%

75%

100%

Type of tweet OT with links and mentionsOT with links and no mentions

OT with mentions and no linksOT without links or mentions

RT with linksRT without links

Endogenous Conversationalists Generalists

Echoers Link Feeders

Evolution

[García-Gavilanes et al. Evolution of Target Audiences. SocInfo’14]

Page 21: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Q2) Users 2011 vs 2013

21

Majority of users remain in the same cluster except the echoers’ group.Increase in Generalists and Link Feeders.Mature users tend to use Twitter more as news media.

[García-Gavilanes et al. Evolution of Target Audiences. SocInfo’14]

Page 22: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

22

Data Mining Cultural

All users

Q1) What is the effect on users from

Human generated recommendations?

Q2) How do user behavior evolve over time?

Q4) What cultural models to use?

Cross-countryQ3) Do all users from

different countries tweet the same?

Q4) Does culture influences the way we

tweet online?

Q5) Can culture influence online interactions with

users from other nations?

Thesis Structure

Cross-country

Page 23: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Q3) Cross-country comparison

•  Data: analysis of one year of Tweets for 10 most active countries

•  Content: languages, sentiment, structure (retweets, hashtags,..)

•  Structure: network (modularity, average path length, reciprocity, connectivity)

23Cross-country

Page 24: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Q3) Activity and Engagement

24

[Garcia-Gavilanes et al. Microblogging without Borders: Differences and Similarities, WebSci’11]

Cross-country

12M active users6M with valid location4M user from 10 most active countries.5B tweets during 2010

.

Page 25: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

25

Countries with more users notnecessarily the most engaged

Cross-country

[Garcia-Gavilanes et al. Microblogging without Borders: Differences and Similarities, WebSci’11]

Q3) Activity and Engagement

Page 26: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

English

Portuguese

Japanese

Spanish

Bahasa−Indonesia

Bahasa−Malay

Korean

Dutch

German

Italian

Arabic

Users

50M 100M 200M 500M 1000M 2000M

Q3) Languages & Sentiment

26

Netherlands >10%,Indonesia >10%,Mexico >10%,South Korea >10%

English is the most common languageMore than 10% in non-english speaking countries

Non-western countries seem to be morePositive

Based in Dodds et al., 2011

Cross-country

[Garcia-Gavilanes et al. Microblogging without Borders: Differences and Similarities, WebSci’11]

Page 27: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Tweet function

27

Country URL (%) Hashtag (%) Mention (%) Retweet (%)Indonesia 14.95 7.63 58.24 9.71Japan 16.30 6.81 39.14 5.65

Brazil 19.23 13.41 45.57 12.80

Netherlands 24.40 18.24 42.33 9.12

UK 27.11 13.03 45.61 11.65

US 32.64 14.32 40.03 11.78

Australia 31.37 14.89 43.27 11.73

Mexico 17.49 12.38 49.79 12.61

South Korea 19.67 5.83 58.02 9.02

Canada 31.09 14.68 42.50 12.50

Some Asian countries seem to chat more (except Japan), use less URLs, hashtags.Asian countries seemed to retweet less.

Cross-country

[Garcia-Gavilanes et al. Microblogging without Borders: Differences and Similarities, WebSci’11]

Page 28: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Q3) Network

28

Country Reciprocity Avg. Clust. Coef

Modularity

Indonesia 0.27 0.06 0.54

Japan 0.32 0.06 0.46

Brazil 0.13 0.07 0.46

Netherlands 0.22 0.10 0.41

UK 0.17 0.10 0.39

US 0.19 0.07 0.42

Australia 0.24 0.10 0.45

Mexico 0.17 0.08 0.36

South Korea 0.28 0.09 0.31

Canada 0.26 0.10 0.56

0 5

10 15 20 25 30 35 40 45

BrazilUK MexicoUSA

NetherlandsAustraliaCanadaIndonesiaSouth_KoreaJapan

Countries

DiameterAvg. Path Length

Reciprocity seems to be significant specially for Asian countries High clustering coefficient and less reciprocity may indicate hierarchical links

Indonesia has highest diameter, which agrees with the modularity coefficient.

[w/ Poblete et al. Do all Birds Tweet the Same?, CIKM, 2011]

Cross-country

Page 29: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Q3) Connectivity

29Cross-country

[w/ Poblete et al. Do all Birds Tweet the Same?, CIKM, 2011]

Page 30: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Q3) Connectivity

30

More self Connected

Cross-country

[w/ Poblete et al. Do all Birds Tweet the Same?, CIKM, 2011]

Page 31: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Q3) Connectivity

31

More connected

Cross-country

[w/ Poblete et al. Do all Birds Tweet the Same?, CIKM, 2011]

Page 32: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

•  Need cultural models to understand differences across countries in

Microblogs

32Cross-country

Page 33: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

33

` Data Mining Cultural

All users

Q1) What is the effect on users from

Human generated recommendations?

Q2) How do user behavior evolve over time?

Q4) What cultural models to use?

Cross-countryQ3) Do all users from

different countries tweet the same?

Q4) Does culture influences the way we tweet online?

Q5) Can culture influence online interactions with

users from other nations?

Thesis Structure

Cultural Models

Page 34: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Culture

34Cultural Models

Page 35: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

WHAT IS CULTURE ?

35Cultural Models

Page 36: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

CULTURE

Software of the mind that distinguishes members of one

group or category of people from others

36Cultural Models

Page 37: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

37Cultural Models

Page 38: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

MEASURE CULTURE•  Geert Hofstede: Cultural dimensions

o  Different cultural dimensions : Individualism, Power Distance and others.

•  Robert Levine: Pace of Life (Geography of time)o  Different perception of time

•  Edward T. Hall: Monochronic vs Polychronic o  Different ways of executing tasks

•  Samuel Huntington: Clash of Civilizationso  Politics of identity replacing politics of interest.

38Cultural Models

Page 39: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Pace of Life

IndividualismPower Distance

39

Levine

Hall

Cultural Models

Page 40: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Can such differences also be captured from online interactions?

40Cultural Models

Page 41: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

41

Data Mining Cultural

All users

Q1) What is the effect on users from

Human generated recommendations?

Q2) How do user behavior evolve over time?

Q4) What cultural models to use?

Cross-countryQ3) Do all users from

different countries tweet the same?

Q5) Does culture influences the way we

tweet online?

Q6) Can culture influence online interactions with

users from other nations?

Thesis Structure

Culture

Page 42: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Q5) Culture in Tweeting Behavior

•  Pace of Life o  Predictability (tweets, mentions)o  Measure entropy of posting tweets in working hours

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

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

42

[Garcia-Gavilanes et al. Cultural Dimensions in Twitter, ICWSM, 2013]

Culture

Page 43: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

43

Tweets Correlation1.  Pace of life1.1 The higher the pace of life the less fraction of users will tweet during working hours1.2 The higher the pace of life, the more predictability

1.1 Users **-0.581.2 Mentions **0.681.2 Tweets **0.62

2. Individualism2.1 User chat less with others in more individualistic countries

2.1 Conversation ***−0.55

3. Power Distance3.1 Users prefer to follow and 3.2 recommend more popular users than themselves in countries with a higher power distance

Users followees **0.62Users and recommended users

**0.56

p ≤ 0.005 (***), 0.005 < p ≤ 0.05 (**), and 0.05 < p ≤ 0.1 (*)

Q5) Correlations

Culture

[Garcia-Gavilanes et al. Cultural Dimensions in Twitter, ICWSM, 2013]

Page 44: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

●●●

● ●

●● ● ●●●

●● ●

● ●● ●●

● ●

IndonesiaVenezuela

MexicoJapanBrazilColombia

ChileSouth Korea ArgentinaPhilippines

Malaysia Spain NetherlandsTurkey UKSouth AfricaSingapore Ireland Canada

FranceBelgiumSweden

AustraliaUnited States

NorwayNew Zealand

Italy

Russia India

Germany

80

85

90

95

100

0 25 50 75

Individualism Index

Fracti

on of

Enga

geme

nt

Introduction 44

Q5) Individualism

[Hong et al.. “Languagematters in twitter: A large scale study” ICWSM 11]

Page 45: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

●●

●●

●●

●●●

●● ●●● ●●

● ●●●●●

●●

Indonesia

Venezuela

Norway

MalaysiaSingapore

Chile Mexico PhilippinesColombia

United StatesSouth Korea IndiaBrazilCanada ArgentinaAustralia

RussiaItalyNew Zealand SpainGermanyJapan FranceSouth AfricaUKIreland TurkeyNetherlands BelgiumSweden

−1000

0

1000

2000

3000

4000

5000

30 60 90

Power Distance Index

In−de

gree I

mbala

nce

Introduction 45

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

Q5) Power

Page 46: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Q5) Why is this important?

46

Indicator Pace of Time: Predictibility

Individualism: Mentions

Power Distance

ImbalanceMentions Users (%)GDP per capita ***0.55 **-0.57 **-0.41 **-0.48

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

In almost all cases, the findings are are also correlated with GDP per capita, education and inequality

Culture

[Garcia-Gavilanes et al. Cultural Dimensions in Twitter, ICWSM, 2013]

p ≤ 0.005 (***), 0.005 < p ≤ 0.05 (**), and 0.05 < p ≤ 0.1 (*)

Page 47: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

47

Data Mining Cultural

All users

Q1) What is the effect on users from

Human generated recommendations?

Q4) What cultural models to use?

Q2) How do user behavior evolve over time?

Cross-countryQ3) Do all users from

different countries tweet the same?

Q5) Does culture influences the way we tweet online?

Q6) Can culture influence online interactions with users from other

nations?

Thesis Structure

Communication

Page 48: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

48Cultural Models

http://commons.wikimedia.org/wiki/File:Clash_of_Civilizations_mapn2.png

Page 49: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

5K country – country pairs

interactions

see you next time @pedro

@John @pedro

49

10 weeks

Q6) Country-country Interactions [ Garcia-Gavilanes et al. Twitter ain’t without Frontiers, CSCW 2014]

Communication

111 countries

3B Geolocated Tweets

Example:

13M Geolocated users

Page 50: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

5K country – country pairsinteractions

50

10 weeks

Q6)Social, economic and cult. features

Communication

Distance

[ Garcia-Gavilanes et al. Twitter ain’t without Frontiers, CSCW 2014]

Page 51: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

51

Q6) Top 1000 strongest edges

Using the gravity model the network is largely clustered according to their geography

Communication

Asia

Latin America

Middle East

The West

Edges: gravity modelForce-directed algorithm

[ Garcia-Gavilanes et al. Twitter ain’t without Frontiers, CSCW 2014]

Page 52: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Edges: Unique MentionsForce-directed algorithm

52

Q6) Top 1000 strongest edges

Communication

[ Garcia-Gavilanes et al. Twitter ain’t without Frontiers, CSCW 2014]

Page 53: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Unique Mentions

53

Q6) Top 1000 strongest edges

Communication

[ Garcia-Gavilanes et al. Twitter ain’t without Frontiers, CSCW 2014]

Page 54: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Introduction 54

Argentina

Australia

Brazil Canada

Chile

Colombia

Dominican Republic

France

Germany

India

Indonesia

Ireland

Italy

Japan

Malaysia

Mexico

Netherlands

New Zealand Nigeria

Philippines

Puerto Rico

Singapore

South Africa

South Korea

SpainSweden

United Kingdom

United States

Venezuela

Q6) Top 50 strongest edges[ Garcia-Gavilanes et al. Twitter ain’t without Frontiers, CSCW, 2014]

Page 55: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

5K country – country pairsinteractions

481  country – country pairs with social, economic and

cultural features

55

10 weeks

Q6)Social, economic and cult. features

Communication

Distance +Economics + Social +Cultural

[ Garcia-Gavilanes et al. Twitter ain’t without Frontiers, CSCW 2014]

Page 56: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

0.45%0.55% 0.57%

0.68%0.80%

0.00#0.10#0.20#0.30#0.40#0.50#0.60#0.70#0.80#0.90#

Gravita/onal%Model%

+Economics% +Social% +Cultural% +%Interac/ons%

r2Adjusted

56

Q5) Features

Higher accuracy at high communication volumes with worse performance as the communication decreases.

The combination of features improves the prediction

Communication

● ●

●●

●●

●●

●●

●●

●●

● ●● ●

● ●

●● ●

●●●

●●

●●

●●

●●

●●

●●

●●

●●

●●

●●

●●

●●●

●●

● ●

●●

●●

●●

●●

●●

●●

●●

●●

●●

●●

●●

●●

●●

●●

●●

● ●

●●

●●

●●

● ●

●●

● ●

●●

● ●

● ●

●●

●●

●●

●●

● ●●

●●

●●

●●

●●

●●

●●

●●

●●

●●

●●

● ●

●●

● ●

●●

●●

0.0 0.2 0.4 0.6 0.8 1.0

0.00.2

0.40.6

0.81.0

communication volume

mode

l's pre

dictio

nM

odel

’s p

redi

ctio

ns

Communication Volume

[ Garcia-Gavilanes et al. Twitter ain’t without Frontiers, CSCW 2014]

Page 57: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

0.45%0.55% 0.57%

0.68%0.80%

0.00#0.10#0.20#0.30#0.40#0.50#0.60#0.70#0.80#0.90#

Gravita/onal%Model%

+Economics% +Social% +Cultural% +%Interac/ons%

r2

r2Adjusted

57

●●

●●

●●

●●

●●●

●●

●●

●●●

●●

●●

●●

●●

● ●

●●

●●

●●

●●

● ●

● ●

●●

●●●

●●

●●

●●●

●●

●●

●●

●●●●

●●

●●

●●

●●●

●●

●●

●●

●●

●●

●●

●●●●

●●

●●

● ●

●●

●●

● ●

●●

●●

● ●●

●●

● ●

●●●

●●

●●

●●●

●●

●●

●●

●●

● ●

●●

● ●

●●

●●

● ●

●●

●●

●●

●●

0.1 0.2 0.5 1.0

0.10.2

0.51.0

communication volume

model

's pred

iction

Q5) Features

Higher accuracy at high communication volumes with worse performance as the communication decreases.

The combination of features improves the prediction

CommunicationCommunication Volume

Mod

el’s

pre

dict

ions

Communication Volume

[ Garcia-Gavilanes et al. Twitter ain’t without Frontiers, CSCW 2014]

Log-scale

Page 58: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Predictor P-value

Trade 6.34   ***

Cultural Dimension 3.91   ***

Gravity Model x Exports 3.78   **Gravity Model 2.79   ***

Language 2.70   .

β(%)Culture

Distance

Economic

Social

Communication 58

Q6)Features

Page 59: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

59

Data Mining Cultural

All users

Q1) What is the effect on users from

Human generated recommendations?

Q2) How do user behavior evolve over time?

Q4) What cultural models to use?

Cross-countryQ3) Do all users from

different countries tweet the same?

Q5) Does culture influences the way we

tweet online?

Q6) Can culture influence online interactions with

users from other nations?

Thesis Structure

Communication

Page 60: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Conclusions & Future Work

Conlusions 60

Human recommendations

Evolution of behavior

•  Recommendations by users have a measurable effect on link formation

•  Adoption of microblogs as a news media rather than as a social network

•  Replicate studies in other platforms•  Cross-cultural recommendation•  Self-organized trends and monetary

consequences•  Cross-cultural evolution

next

Page 61: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Conlusions 61

Cross-country comparison

Tweeting behavior

Communication

•  The collective behavior differ in certain characteristics: chatting engagement, reciprocity, modularity, communities.

•  National culture determine the temporal patterns with which Twitter users post, or the extent to which they mention, follow, recommend and befriend others.

•  In addition to distance, socio-economic and cultural features also impact international communication.

Conclusions & Future Work

next

•  Application to improve communication across- cultures like machine translation (already existent: WeChat)

•  China and the rest of the world: two online worlds that will meet

Page 62: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Thank you QUESTIONS?

@[email protected]

(Ph.D survivor)

62The End

Page 63: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

The End 63

Acknowledgements: Ricardo Baeza-Yates, Daniele Quercia, Yelena MejovaNeil O’Hare, Luca Maria Aiello, Alejandro Jaimes, Barbara Poblete,Marcelo Mendoza, Andreas Kaltenbrunner, Diego Sa ́ez-Trumper, Pablo Aragón, David Laniado, Ilaria Bordino, Sara Haijan, Amin Mantrach .

Acknowledgements

Page 64: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Publications•  Ruth García-Gavilanes, Barbara Poblete, Marcelo Mendoza, Alejandro Jaimes.

Microblogging without Borders: Differences and Similarities. In The 3rd International Conference on Information and Knowledge Management (Websci), ACM, 2011.

•  Barbara Poblete, Ruth García-Gavilanes, Marcelo Mendoza, Alejandro Jaimes. Do All Birds Tweet the Same? Characterizing Twitter Around the World. In The 20th International Conference on Information and Knowledge Management (CIKM), ACM, 2011

•  Ruth García-Gavilanes, Neil O’Hare, Luca Maria Aiello, Alejandro Jaimes. Follow My Friends This Friday! An Analysis of Human- generated Friendship Recommendations. In The 5th International Conference on Social Informatics (SocInfo), Springer 2013. [Best paper award]

•  Ruth García-Gavilanes, Andreas Kaltenbrunner, Diego Sa ́ez-Trumper, Ricardo Baeza-Yates, Pablo Arago ̀n and David Laniado. Who are my Audiences? A Study of the Evolution of Target Audiences in Microblogs. In The 6th International Conference on Social Informatics (SocInfo), Springer 2014.

•  Ruth García-Gavilanes, Daniele Quercia, Alejandro Jaimes. Cultural Dimensions in Twitter: Time, Individualism and Power. In The 7th International AAAI Conference on WebLogs and Social Media (ICWSM), 2013. [Honorable mention]

•  Ruth García-Gavilanes, Yelena Mejova, Daniele Quercia. Twitter ain’t Without Frontiers: Economic, Social, and Cultural Boundaries in International Communication. In The 17th ACM Conference on Computer Supported Cooperative Work and Social Computing (CSCW), 2014.

The End 64

Page 65: USER BEHAVIOR IN MICROBLOGS WITH A CULTURAL EMPHASIS

Selected References•  Haewoon Kwak, Changhyun Lee, Hosung Park, and Sue Moon. What is Twitter,

a Social Network or a News Media? In Proceedings of the 19th international conference on World Wide Web, ACM 2010

•  Meeyoung Cha, Hamed Haddadi, Fabricio Benevenuto, and Krishna P. Gummadi. Measuring User Influence in Twitter: The Million Follower Fallacy. In International AAAI Conference on Weblogs and Social Media (ICWSM)

•  Katharina Reinecke, Minh Khoa Nguyen, Abraham Bernstein, Michael Naf, and Krzysztof Z. Gajos. Doodle Around the World: Online Scheduling Behavior Reflects Cultural Differences in Time Perception and Group Decision-Making. In Proceedings of the 16th ACM Conference on Computer Supported Cooperative Work and Social Computing (CSCW’13)

•  Peter S. Dodds, Kameron D. Harris, Isabel M. Kloumann, Catherine A. Bliss, and Christopher M. Danforth. Temporal patterns of happiness and information in a global social network: Hedonometrics and Twitter. PLOS ONE, 2011.

•  Geert Hofstede, Gert Jan Hofstede, and Michael Minkov. Cultures and Organizations: Software of the Mind. McGraw-Hill, 2010.

The End 65