SlideShare a Scribd company logo
Introduction Results. Event analysis Discussion Conclusions 
Analysis of the Evolution of Events on Online 
Social Networks 
E. del Val, M. Rebollo and V. Botti 
Grupo Tec. Inform.-Inteligencia Artificial 
Universitat Politècnica de València 
CSS 2014 
@mrebollo UPV 
Analysis of the Evolution of Events on Online Social Networks
Introduction Results. Event analysis Discussion Conclusions 
Problem 
Analysis of user behavior 
How user interactions evolve in a social network associated to the 
realization of a scheduled event in the real world. 
4 types of events are considered 
TV shows 
socio-political 
conferences 
keynotes 
@mrebollo UPV 
Analysis of the Evolution of Events on Online Social Networks
Introduction Results. Event analysis Discussion Conclusions 
The Hypothesis 
There are significative differences in the behavior of the 
participants in each type of event 
@mrebollo UPV 
Analysis of the Evolution of Events on Online Social Networks
Introduction Results. Event analysis Discussion Conclusions 
Data set 
twits containing the hashtag of the event are retrieved 
interaction-based network: mentions, replies and retweets 
focus on scheduled events 
temporally annotated network (nodes and links) 
empirical analysis 
@mrebollo UPV 
Analysis of the Evolution of Events on Online Social Networks
Introduction Results. Event analysis Discussion Conclusions 
Events 
TV shows 
La voz 
Topchef 
BreakingBad 
OperacionPalace 
Keynotes 
applekeynote 
nuevosiphone 
innovationreinvented (Nokia) 
Socio-political 
lomce 
viacatalana 
EU elections debate 
Conferences 
TEDValencia 
seo4seos 
Twitter awards 2013 
InternetOfThings forum 
CW’13 (web conference) 
@mrebollo UPV 
Analysis of the Evolution of Events on Online Social Networks
Introduction Results. Event analysis Discussion Conclusions 
Event characterization 
Event N E clust. d path comp. k m GC %sl 
#lomce #24O 61,653 97,570 0.07 27 6.93 8,088 1.58 0.73 49,164 10.80 
#via 41,166 76,094 0.07 23 8.28 8,705 1.85 0.56 30,745 12.19 
catalana 
#topchef12 26,044 27,155 0.05 25 8.74 10,689 1.04 0.66 12,794 12.29 
#lavoz 45,914 39,891 0.07 9 2.11 19,398 0.87 0.81 17,941 6.95 
#breakingbad 151,473 120,661 0.05 13 3.24 67,060 0.80 0.72 71,130 14.26 
#operacion 107,606 195,470 0.08 23 8.26 19,504 1.82 0.49 85,768 15.06 
Palace 
#apple 3,367 1,729 0.04 4 1.27 1,827 0.51 0.93 700 1.53 
keynote 
#nuevos 9,509 10,600 0.05 9 2.09 1,227 1.12 0.62 7,799 6.47 
iPhone 
#innovation 110 95 0.04 3 1.34 32 0.86 0.83 26 10.00 
reinvented 
#IoTWF 4,150 17,545 0.22 9 3.96 330 4.23 0.42 3,680 30.83 
#cw13 1,051 2,608 0.20 9 3.90 60 2.48 0.56 966 19.76 
#seo4seos 367 1,474 0.35 6 2.91 16 4.02 0.30 347 31.07 
#tedx 325 843 0.17 8 3.60 45 2.59 0.32 276 8.60 
valencia 
@mrebollo UPV 
Analysis of the Evolution of Events on Online Social Networks
Introduction Results. Event analysis Discussion Conclusions 
Message type 
tv: linear, global, during 
soc: linear, inter., always 
keyn: global, before 
conf: linear, inter., during 
45000 
40000 
35000 
30000 
25000 
20000 
15000 
10000 
5000 
0 
0 50 100 150 200 250 300 350 
num tweets 
snapshot 
global 
retweets 
mentions 
replyTo 
(a) TV show: #topchef12. 
60000 
50000 
40000 
30000 
20000 
10000 
0 
0 50 100 150 200 250 300 350 
num tweets 
snapshot 
global 
retweets 
mentions 
replyTo 
(b) Socio-political: #viacatalana 
6000 
5000 
4000 
3000 
2000 
1000 
0 
0 50 100 150 200 250 300 350 
num tweets 
snapshot 
global 
retweets 
mentions 
replyTo 
(c) Keynote: #applekeynote 
1000 
800 
600 
400 
200 
0 
0 100 200 300 400 500 600 700 
num tweets 
snapshot 
global 
retweets 
mentions 
replyTo 
(d) Conference: #tedxValencia 
Figure 2: Evolution of the number of global and individual messages (mentions, retweets, and reply to) in different type of events. 
@mrebollo UPV 
Analysis of the Evolution of Events on Online Social Networks 
9
Introduction Results. Event analysis Discussion Conclusions 
Network size (links and nodes) 
tv: always, similar 
soc: always, ""links 
keyn: before, ""links 
conf: but after, ""links 
30000 
25000 
20000 
15000 
10000 
5000 
0 
0 50 100 150 200 250 300 350 
num links or nodes 
snapshot 
links 
nodes 
(a) TV show: #topchef12. 
80000 
70000 
60000 
50000 
40000 
30000 
20000 
10000 
0 
0 50 100 150 200 250 300 350 
num links or nodes 
snapshot 
links 
nodes 
(b) Socio-political: #viacatalana. 
3500 
3000 
2500 
2000 
1500 
1000 
500 
0 
0 50 100 150 200 250 300 350 
num links or nodes 
snapshot 
links 
nodes 
(c) Keynote: #applekeynote. 
900 
800 
700 
600 
500 
400 
300 
200 
100 
0 
0 100 200 300 400 500 600 700 
num links or nodes 
snapshot 
links 
nodes 
(d) Conference: #tedxValencia. 
Figure 3: Evolution of the number of nodes and links in different type of events. 
the number of nodes and links increases moderately. People in the analyzed events prefer to talk and interact 
before the event rather than during the keynote. 
In the analyzed conference networks, the number of nodes grows rapidly before the event starts (see Figure 
3d). Then, during the event, there is also an important increase in the number of nodes. Towards the end of the 
event as well as after the event, the number of nodes remains almost constant. If the conference consists on two 
or three days, during the first day is when a most significant increase in the number of new nodes occurs. The 
number of links evolves similarly as the nodes. However, the increase in the number of interactions is produced 
at a higher rate. This means that assistants to a conference are more social and interact with other assistants. 
This behavior is similar to behavior of participants in socio-political networks. 
@mrebollo UPV 
Analysis of the Evolution of Events on Online Social Networks
Introduction Results. Event analysis Discussion Conclusions 
Symmetric links 
tv: low, decreasing 
soc: low, constant 
keyn: lowest 
conf: tipically high, 
constant 
40 
35 
30 
25 
20 
15 
10 
5 
0 
% of symmetric links 
0 50 100 150 200 250 300 350 
symmetric links 
snapshot 
(a) TV show: #topchef12. 
40 
35 
30 
25 
20 
15 
10 
5 
0 
% of symmetric links 
0 50 100 150 200 250 300 350 
symmetric links 
snapshot 
(b) Socio-political: #viacatalana. 
40 
35 
30 
25 
20 
15 
10 
5 
0 
% of symmetric links 
0 50 100 150 200 250 300 350 
symmetric links 
snapshot 
(c) Keynote: #applekeynote. 
40 
35 
30 
25 
20 
15 
10 
5 
0 
% of symmetric links 
0 100 200 300 400 500 600 700 
symmetric links 
snapshot 
(d) Conference: #tedxValencia. 
Figure 4: Evolution of the number of symmetric links in different type of events. 
@mrebollo UPV 
Analysis of the Evolution of Events on Online Social Networks 
12
Introduction Results. Event analysis Discussion Conclusions 
Cummulative degree distrib. and CCDF 
@mrebollo UPV 
Analysis of the Evolution of Events on Online Social Networks
Introduction Results. Event analysis Discussion Conclusions 
Path length and diameter 
all: grows before and 
remains constant 
non significative 
differences 
30 
25 
20 
15 
10 
5 
0 
path Length 
0 50 100 150 200 250 300 350 
num steps 
timeStep 
diameter 
(a) TV show: #topchef12. 
30 
25 
20 
15 
10 
5 
0 
path Length 
0 50 100 150 200 250 300 350 
num steps 
timeStep 
diameter 
(b) Socio-political: #viacatalana. 
4 
3.5 
3 
2.5 
2 
1.5 
1 
path Length 
0 50 100 150 200 250 300 350 
num steps 
timeStep 
diameter 
(c) Keynote: #applekeynote. 
9 
8 
7 
6 
5 
4 
3 
2 
1 
path Length 
0 100 200 300 400 500 600 700 
num steps 
timeStep 
diameter 
(d) Conference: #tedxValencia. 
Figure 6: Evolution of the average path length and diameter in different type of events. 
@mrebollo UPV 
Analysis of the Evolution of Events on Online Social Networks 
15
Introduction Results. Event analysis Discussion Conclusions 
Clustering 
not significative in the 
evolution 
differences in the values 
("conf, ## keyn) 
0.4 
0.35 
0.3 
0.25 
0.2 
0.15 
0.1 
0.05 
0 
clustering dynamics 
0 50 100 150 200 250 300 350 
Clustering Degree 
timeStep 
(a) TV show: #topchef12. 
0.4 
0.35 
0.3 
0.25 
0.2 
0.15 
0.1 
0.05 
0 
clustering dynamics 
0 50 100 150 200 250 300 350 
Clustering Degree 
timeStep 
(b) Socio-political: #viacatalana. 
0.4 
0.35 
0.3 
0.25 
0.2 
0.15 
0.1 
0.05 
0 
clustering dynamics 
0 50 100 150 200 250 300 350 
Clustering Degree 
timeStep 
(c) Keynote: #applekeynote. 
0.4 
0.35 
0.3 
0.25 
0.2 
0.15 
0.1 
0.05 
0 
clustering dynamics 
0 100 200 300 400 500 600 700 
Clustering Degree 
timeStep 
(d) Conference: #tedxValencia. 
Figure 7: Evolution of the average clustering in different type of events. 
@mrebollo UPV 
Analysis of the Evolution of Events on Online Social Networks 
16
Introduction Results. Event analysis Discussion Conclusions 
Nodes in the giant component 
all: created before the 
event 
tv and keyn: low 
soc and conf: high 
100 
80 
60 
40 
20 
0 
% of nodes 
0 50 100 150 200 250 300 350 
% of nodes that are in the giant component 
timeStep 
(a) TV show: #topchef12. 
100 
80 
60 
40 
20 
0 
% of nodes 
0 50 100 150 200 250 300 350 
% of nodes that are in the giant component 
timeStep 
(b) Socio-political: #viacatalana. 
100 
80 
60 
40 
20 
0 
% of nodes 
0 50 100 150 200 250 300 350 
% of nodes that are in the giant component 
timeStep 
(c) Keynote: #applekeynote. 
100 
80 
60 
40 
20 
0 
% of nodes 
0 100 200 300 400 500 600 700 
% of nodes that are in the giant component 
timeStep 
(d) Conference: #tedxValencia. 
Figure 8: Evolution of the % of nodes that are part of the giant component in different type of events. 
@mrebollo UPV 
Analysis of the Evolution of Events on Online Social Networks 
17
Introduction Results. Event analysis Discussion Conclusions 
Betweenness 
tv: official + celebrities 
soc: politics, journalists, 
bloggers 
keyn: media, tech sites, 
bloggers 
conf: official + speakers 
 
 
 
 
 
 
 
 
        
 
 
 
 
 
 
 
 
 
 
 
 
(a) TV show: #topchef12. 
 
 
 
 
 
 
 
 
 
        
 
 
 
 
 
 
 
 
 
 
 
 
(b) Socio-political: #viacatalana. 
 
 
 
 
 
 
 
 
 
        
 
 
 
 
 
 
 
 
 
 
 
  
 
(c) Keynote: #applekeynote. 
 
 
 
 
 
 
 
 
 
        
 
 
 
 
 
 
 
 
 
 
 
 
(d) Conference: #tedxValencia. 
Figure 9: Evolution of the betweenness of the ten nodes with the highest betweenness value in different type of events. 
The nodes with the highest betweenness value in the analyzed keynote networks are the nodes that represent 
media, technological web pages, and bloggers. In general, the value of betweenness of these nodes starts 
increasing before the event and after the event (see Figure 9c). However, during the event, the values of 
betweenness remain constant since there are not a high number of interactions (new links) between nodes. 
There is a big difference between the nodes that represent media or web pages and the rest of the nodes that 
represent bloggers or users. 
In the analyzed conference networks, the nodes with the highest betweenness are official accounts and 
speakers. In general, the official account has the highest betweenness value with respect the betweenness of 
the speakers (see Figure 9d). During the event, the betweenness of the official account increases at a higher 
rate than the speakers account. Among the nodes that represent the speakers there is also a difference between 
those that participate in the first sessions and the speakers that participate in later sessions. The betweenness 
of the speakers that participate in the first sessions increases from the beginning. However, the betweenness of 
the speakers that participate in later sessions is initially almost constant and starts to increase once the speaker 
participates in the conference. After the event the betweenness of all nodes remains almost constant. 
@mrebollo UPV 
Analysis of the Evolution of Events on Online Social Networks
Introduction Results. Event analysis Discussion Conclusions 
Indegree and outdegree 
tv, soc and keyn: indegree 
same as betweenness; 
outdegree anonymous 
conf: balanced 
 
 
 
 
 
 
 
 
 
 
        
 
 
 
 
 
 
 
 
 
 
 
 
(a) TV show: #topchef12. Indegree 
 
 
 
 
 
 
 
 
 
 
 
        
 
 
 
 
 
 
 
 
 
 
 
 
(b) TV show: #topchef12. Outdegree 
 
 
 
 
 
 
 
        
 
 
 
 
 
 
 
 
 
 
 
 
(c) Socio-political: #viacatalana. Indegree 
 
 
 
 
 
 
 
 
 
        
 
 
 
 
 
 
 
 
 
 
 
 
(d) Socio-political: #viacatalana. Outdegree 
 
 
 
 
 
 
 
        
 
 
 
 
 
 
 
 
 
  
 
 
 
(e) Keynote: #applekeynote. Indegree 
 
 
 
 
 
 
 
 
        
 
 
 
 
 
 
 
 
 
 
 
 
 
 
  
(f) Keynote: #applekeynote. Outdegree 
 
 
 
 
 
 
 
        
 
 
 
 
 
 
 
 
 
 
 
 
(g) Conference: #tedxValencia. Indegree 
 
 
 
 
 
 
 
 
        
 
 
 
 
 
 
 
 
 
 
 
 
(h) Conference: #tedxValencia. Outdegree 
21 
Figure 10: Evolution of the indegree and outdegree of the ten nodes with the highest indegree and outdegree value in different type 
of events. 
@mrebollo UPV 
Analysis of the Evolution of Events on Online Social Networks
Introduction Results. Event analysis Discussion Conclusions 
Eigenvector 
"" heterogeneous (even in 
the same event type) 
not significative 
 
 
 
 
 
 
        
 
 
 
 
 
 
 
 
 
 
 
 
(a) TV show: #topchef12. 
 
 
 
 
 
 
        
 
 
 
 
 
 
 
 
 
 
 
 
(b) Socio-political: #viacatalana. 
 
 
 
 
 
 
 
 
 
 
 
  
 
 
 
        
 
 
 
 
 
(c) Keynote: #applekeynote. 
 
 
 
 
 
 
        
 
 
 
 
 
 
 
 
 
 
 
 
(d) Conference: #tedxValencia. 
Figure 11: Evolution of the eigenvector of the ten nodes with the highest eigenvector value in different type of events. 
connection join the network and the eigenvector of the speakers decreases steadily. In contrast, the speakers 
that participate in the event later on have an eigenvector that increases smoothly before their participation in 
the event. Then, when the speakers participate in the event, their eigenvector increases sharply. This means 
that other nodes with a high degree of connection establish a connection with the speakers. After this increase, 
the eigenvector centrality of the last speakers remains almost constant or there is a small decrease. When the 
event is going to finish, the eigenvector of all the nodes remains almost constant. 
6. Discussion 
After the analysis of the networks, we observed that the networks generated from the Twitter events can be 
@mrebollo classified in two main groups based on the type of interactions between users. One group consists of the TV 
UPV 
Analysis of the Evolution of Events on Online Social Networks 
show and keynote networks. The other group consists of the socio-political and conference networks. 
In the group of TV show and keynote networks, users tend to participate in the event through global mes-sages. 
The majority of interactions are unidirectional from unknown users to official accounts or celebrities.
Introduction Results. Event analysis Discussion Conclusions 
Discussion 
two clearly differenced types 
TV shows and keynotes 
global, undirectional messages 
asymmetric: celebrities - annonymous 
low clustering and long pathes 
TV: after & before; keyn: during 
socio-political and conferences 
real communication among participants 
higher symmetry, reciprocity 
conf: official account more participative 
@mrebollo UPV 
Analysis of the Evolution of Events on Online Social Networks
Introduction Results. Event analysis Discussion Conclusions 
Conclusions 
Conclusions 
official event account barely influences 
communities created around ’persons of interest’ 
giant component created before event 
2 groups clearly differencied 
significant differences among the 4 groups 
Future work 
follow user activity to complete de information 
include decay in the links 
include specific temporal measures; multiplex structure 
create models for events and user profiles 
@mrebollo UPV 
Analysis of the Evolution of Events on Online Social Networks

More Related Content

Viewers also liked

Guía para el uso de redes sociales en el aprendizaje inverso
Guía para el uso de redes sociales en el aprendizaje inversoGuía para el uso de redes sociales en el aprendizaje inverso
Guía para el uso de redes sociales en el aprendizaje inverso
Miguel Rebollo
 
Cómo crear mi PLE
Cómo crear mi PLECómo crear mi PLE
Cómo crear mi PLE
Miguel Rebollo
 
Comunica 2016
Comunica 2016Comunica 2016
Comunica 2016
Miguel Rebollo
 
Community detection algorithms
Community detection algorithmsCommunity detection algorithms
Community detection algorithms
Alireza Andalib
 
Supportive consensus for smart grid management
Supportive consensus for smart grid managementSupportive consensus for smart grid management
Supportive consensus for smart grid management
Miguel Rebollo
 
Community detection in social networks[1]
Community detection in social networks[1]Community detection in social networks[1]
Community detection in social networks[1]
sdnumaygmailcom
 
La (poca) soledad del corredor de fondo
La (poca) soledad del corredor de fondoLa (poca) soledad del corredor de fondo
La (poca) soledad del corredor de fondo
Miguel Rebollo
 
Consensus in Smart Grids for Decentralized Energy Management
Consensus in Smart Grids for Decentralized Energy ManagementConsensus in Smart Grids for Decentralized Energy Management
Consensus in Smart Grids for Decentralized Energy Management
Miguel Rebollo
 
Decentralized Group AHP in Multilayer Networks by Consensus
Decentralized Group AHP in Multilayer Networks by ConsensusDecentralized Group AHP in Multilayer Networks by Consensus
Decentralized Group AHP in Multilayer Networks by Consensus
Miguel Rebollo
 
Community Detection
Community Detection Community Detection
Community Detection
Kanika Kanwal
 
Análisis de sentimientos en Twitter mediante HMM
Análisis de sentimientos en Twitter mediante HMMAnálisis de sentimientos en Twitter mediante HMM
Análisis de sentimientos en Twitter mediante HMM
Miguel Rebollo
 
U-Tool: A Urban-Toolkit for enhancing city maps through citizens’ activity
U-Tool: A Urban-Toolkit for enhancing city maps through citizens’ activityU-Tool: A Urban-Toolkit for enhancing city maps through citizens’ activity
U-Tool: A Urban-Toolkit for enhancing city maps through citizens’ activity
Miguel Rebollo
 
Meilleur travail du monde
Meilleur travail du mondeMeilleur travail du monde
Meilleur travail du monde
Miguel Rebollo
 

Viewers also liked (13)

Guía para el uso de redes sociales en el aprendizaje inverso
Guía para el uso de redes sociales en el aprendizaje inversoGuía para el uso de redes sociales en el aprendizaje inverso
Guía para el uso de redes sociales en el aprendizaje inverso
 
Cómo crear mi PLE
Cómo crear mi PLECómo crear mi PLE
Cómo crear mi PLE
 
Comunica 2016
Comunica 2016Comunica 2016
Comunica 2016
 
Community detection algorithms
Community detection algorithmsCommunity detection algorithms
Community detection algorithms
 
Supportive consensus for smart grid management
Supportive consensus for smart grid managementSupportive consensus for smart grid management
Supportive consensus for smart grid management
 
Community detection in social networks[1]
Community detection in social networks[1]Community detection in social networks[1]
Community detection in social networks[1]
 
La (poca) soledad del corredor de fondo
La (poca) soledad del corredor de fondoLa (poca) soledad del corredor de fondo
La (poca) soledad del corredor de fondo
 
Consensus in Smart Grids for Decentralized Energy Management
Consensus in Smart Grids for Decentralized Energy ManagementConsensus in Smart Grids for Decentralized Energy Management
Consensus in Smart Grids for Decentralized Energy Management
 
Decentralized Group AHP in Multilayer Networks by Consensus
Decentralized Group AHP in Multilayer Networks by ConsensusDecentralized Group AHP in Multilayer Networks by Consensus
Decentralized Group AHP in Multilayer Networks by Consensus
 
Community Detection
Community Detection Community Detection
Community Detection
 
Análisis de sentimientos en Twitter mediante HMM
Análisis de sentimientos en Twitter mediante HMMAnálisis de sentimientos en Twitter mediante HMM
Análisis de sentimientos en Twitter mediante HMM
 
U-Tool: A Urban-Toolkit for enhancing city maps through citizens’ activity
U-Tool: A Urban-Toolkit for enhancing city maps through citizens’ activityU-Tool: A Urban-Toolkit for enhancing city maps through citizens’ activity
U-Tool: A Urban-Toolkit for enhancing city maps through citizens’ activity
 
Meilleur travail du monde
Meilleur travail du mondeMeilleur travail du monde
Meilleur travail du monde
 

Similar to Analysis of the Evolution of Events on Online Social Networks

Is software engineering research addressing software engineering problems?
Is software engineering research addressing software engineering problems?Is software engineering research addressing software engineering problems?
Is software engineering research addressing software engineering problems?
Gail Murphy
 
Creative founder mock pitch
Creative founder mock pitchCreative founder mock pitch
Creative founder mock pitch
Weiwei Hsu
 
Design + Devops: What We've Learned from Our Developer Friends
Design + Devops: What We've Learned from Our Developer FriendsDesign + Devops: What We've Learned from Our Developer Friends
Design + Devops: What We've Learned from Our Developer Friends
UXPA International
 
Telescope Pitch Deck
Telescope Pitch DeckTelescope Pitch Deck
Telescope Pitch Deck
Nino Panes
 
JavaCro'14 - Going Digital with Java EE - Peter Pilgrim
JavaCro'14 - Going Digital with Java EE - Peter PilgrimJavaCro'14 - Going Digital with Java EE - Peter Pilgrim
JavaCro'14 - Going Digital with Java EE - Peter Pilgrim
HUJAK - Hrvatska udruga Java korisnika / Croatian Java User Association
 
JavaCro 2014 Digital Development with Java EE and Java Platform
JavaCro 2014 Digital Development with Java EE and Java PlatformJavaCro 2014 Digital Development with Java EE and Java Platform
JavaCro 2014 Digital Development with Java EE and Java Platform
Peter Pilgrim
 
[ICDE 2014] Incremental Cluster Evolution Tracking from Highly Dynamic Networ...
[ICDE 2014] Incremental Cluster Evolution Tracking from Highly Dynamic Networ...[ICDE 2014] Incremental Cluster Evolution Tracking from Highly Dynamic Networ...
[ICDE 2014] Incremental Cluster Evolution Tracking from Highly Dynamic Networ...
Pei Lee
 
CML's Presentation at FengChia University
CML's Presentation at FengChia UniversityCML's Presentation at FengChia University
CML's Presentation at FengChia University
Tunghai University
 
Social media campaign in China
Social media campaign in ChinaSocial media campaign in China
Social media campaign in China
EASTWEST Public Relations
 
Sp150502ss
Sp150502ssSp150502ss
Sp150502ss
Stuart Palmer
 
Sharifah Amirah
Sharifah AmirahSharifah Amirah
Sharifah Amirah
evensys
 
Sharifah Amirah
Sharifah  AmirahSharifah  Amirah
Sharifah Amirah
evensys
 
Smart Hydroponic Plant Growing System using IoT
Smart Hydroponic Plant Growing System using IoTSmart Hydroponic Plant Growing System using IoT
Smart Hydroponic Plant Growing System using IoT
Gustavo Sanchez Collado
 
WIPAC Monthly - February 2020
WIPAC Monthly - February 2020WIPAC Monthly - February 2020
WIPAC Monthly - February 2020
Water Industry Process Automation & Control
 
Beyond the Code Itself: How Programmers Really Look at Pull Requests
Beyond the Code Itself: How Programmers Really Look at Pull RequestsBeyond the Code Itself: How Programmers Really Look at Pull Requests
Beyond the Code Itself: How Programmers Really Look at Pull Requests
Denae Ford
 
Network Intelligence Driven Human Behavior Modeling
Network Intelligence Driven Human Behavior ModelingNetwork Intelligence Driven Human Behavior Modeling
Network Intelligence Driven Human Behavior ModelingFahim Kawsar
 
Listening to the pulse of our cities with Stream Reasoning (and few more tech...
Listening to the pulse of our cities with Stream Reasoning (and few more tech...Listening to the pulse of our cities with Stream Reasoning (and few more tech...
Listening to the pulse of our cities with Stream Reasoning (and few more tech...
Emanuele Della Valle
 
WIPAC Monthly March 2020
WIPAC Monthly March 2020WIPAC Monthly March 2020
Mining the Social Web - Lecture 2 - T61.6020
Mining the Social Web - Lecture 2 - T61.6020Mining the Social Web - Lecture 2 - T61.6020
Mining the Social Web - Lecture 2 - T61.6020
Michael Mathioudakis
 
Safeguarding Abila: Real-time Streaming Analysis
Safeguarding Abila: Real-time Streaming AnalysisSafeguarding Abila: Real-time Streaming Analysis
Safeguarding Abila: Real-time Streaming Analysis
Parang Saraf
 

Similar to Analysis of the Evolution of Events on Online Social Networks (20)

Is software engineering research addressing software engineering problems?
Is software engineering research addressing software engineering problems?Is software engineering research addressing software engineering problems?
Is software engineering research addressing software engineering problems?
 
Creative founder mock pitch
Creative founder mock pitchCreative founder mock pitch
Creative founder mock pitch
 
Design + Devops: What We've Learned from Our Developer Friends
Design + Devops: What We've Learned from Our Developer FriendsDesign + Devops: What We've Learned from Our Developer Friends
Design + Devops: What We've Learned from Our Developer Friends
 
Telescope Pitch Deck
Telescope Pitch DeckTelescope Pitch Deck
Telescope Pitch Deck
 
JavaCro'14 - Going Digital with Java EE - Peter Pilgrim
JavaCro'14 - Going Digital with Java EE - Peter PilgrimJavaCro'14 - Going Digital with Java EE - Peter Pilgrim
JavaCro'14 - Going Digital with Java EE - Peter Pilgrim
 
JavaCro 2014 Digital Development with Java EE and Java Platform
JavaCro 2014 Digital Development with Java EE and Java PlatformJavaCro 2014 Digital Development with Java EE and Java Platform
JavaCro 2014 Digital Development with Java EE and Java Platform
 
[ICDE 2014] Incremental Cluster Evolution Tracking from Highly Dynamic Networ...
[ICDE 2014] Incremental Cluster Evolution Tracking from Highly Dynamic Networ...[ICDE 2014] Incremental Cluster Evolution Tracking from Highly Dynamic Networ...
[ICDE 2014] Incremental Cluster Evolution Tracking from Highly Dynamic Networ...
 
CML's Presentation at FengChia University
CML's Presentation at FengChia UniversityCML's Presentation at FengChia University
CML's Presentation at FengChia University
 
Social media campaign in China
Social media campaign in ChinaSocial media campaign in China
Social media campaign in China
 
Sp150502ss
Sp150502ssSp150502ss
Sp150502ss
 
Sharifah Amirah
Sharifah AmirahSharifah Amirah
Sharifah Amirah
 
Sharifah Amirah
Sharifah  AmirahSharifah  Amirah
Sharifah Amirah
 
Smart Hydroponic Plant Growing System using IoT
Smart Hydroponic Plant Growing System using IoTSmart Hydroponic Plant Growing System using IoT
Smart Hydroponic Plant Growing System using IoT
 
WIPAC Monthly - February 2020
WIPAC Monthly - February 2020WIPAC Monthly - February 2020
WIPAC Monthly - February 2020
 
Beyond the Code Itself: How Programmers Really Look at Pull Requests
Beyond the Code Itself: How Programmers Really Look at Pull RequestsBeyond the Code Itself: How Programmers Really Look at Pull Requests
Beyond the Code Itself: How Programmers Really Look at Pull Requests
 
Network Intelligence Driven Human Behavior Modeling
Network Intelligence Driven Human Behavior ModelingNetwork Intelligence Driven Human Behavior Modeling
Network Intelligence Driven Human Behavior Modeling
 
Listening to the pulse of our cities with Stream Reasoning (and few more tech...
Listening to the pulse of our cities with Stream Reasoning (and few more tech...Listening to the pulse of our cities with Stream Reasoning (and few more tech...
Listening to the pulse of our cities with Stream Reasoning (and few more tech...
 
WIPAC Monthly March 2020
WIPAC Monthly March 2020WIPAC Monthly March 2020
WIPAC Monthly March 2020
 
Mining the Social Web - Lecture 2 - T61.6020
Mining the Social Web - Lecture 2 - T61.6020Mining the Social Web - Lecture 2 - T61.6020
Mining the Social Web - Lecture 2 - T61.6020
 
Safeguarding Abila: Real-time Streaming Analysis
Safeguarding Abila: Real-time Streaming AnalysisSafeguarding Abila: Real-time Streaming Analysis
Safeguarding Abila: Real-time Streaming Analysis
 

More from Miguel Rebollo

IA en entornos rurales aplicada a la viticultura
IA en entornos rurales aplicada a la viticulturaIA en entornos rurales aplicada a la viticultura
IA en entornos rurales aplicada a la viticultura
Miguel Rebollo
 
Inteligencia artificial para una transformación inteligente
Inteligencia artificial para una transformación inteligenteInteligencia artificial para una transformación inteligente
Inteligencia artificial para una transformación inteligente
Miguel Rebollo
 
GTG-CoL: A Decentralized Federated Learning Based on Consensus for Dynamic N...
 GTG-CoL: A Decentralized Federated Learning Based on Consensus for Dynamic N... GTG-CoL: A Decentralized Federated Learning Based on Consensus for Dynamic N...
GTG-CoL: A Decentralized Federated Learning Based on Consensus for Dynamic N...
Miguel Rebollo
 
Co-Learning: Consensus-based Learning for Multi-Agent Systems
 Co-Learning: Consensus-based Learning for Multi-Agent Systems Co-Learning: Consensus-based Learning for Multi-Agent Systems
Co-Learning: Consensus-based Learning for Multi-Agent Systems
Miguel Rebollo
 
Análisis de la red de autores de ciencia ficción de Clarkesworld
Análisis de la red de autores de ciencia ficción de ClarkesworldAnálisis de la red de autores de ciencia ficción de Clarkesworld
Análisis de la red de autores de ciencia ficción de Clarkesworld
Miguel Rebollo
 
Y sin embargo... se mueve. Dinámica de las redes complejas
Y sin embargo... se mueve. Dinámica de las redes complejasY sin embargo... se mueve. Dinámica de las redes complejas
Y sin embargo... se mueve. Dinámica de las redes complejas
Miguel Rebollo
 
Exámenes en grupo y pruebas de corrección como alternativas a la evaluación
Exámenes en grupo y pruebas de corrección como alternativas a la evaluaciónExámenes en grupo y pruebas de corrección como alternativas a la evaluación
Exámenes en grupo y pruebas de corrección como alternativas a la evaluación
Miguel Rebollo
 
Gamification. Key Concepts
Gamification. Key ConceptsGamification. Key Concepts
Gamification. Key Concepts
Miguel Rebollo
 
Using Distributed Risk Maps by Consensus as a Complement to Contact Tracing Apps
Using Distributed Risk Maps by Consensus as a Complement to Contact Tracing AppsUsing Distributed Risk Maps by Consensus as a Complement to Contact Tracing Apps
Using Distributed Risk Maps by Consensus as a Complement to Contact Tracing Apps
Miguel Rebollo
 
Distributed Ledger and Robust Consensus for Agreements
Distributed Ledger and Robust Consensus for AgreementsDistributed Ledger and Robust Consensus for Agreements
Distributed Ledger and Robust Consensus for Agreements
Miguel Rebollo
 
Detección de nodos tramposos en procesos de consenso en redes
Detección de nodos tramposos en procesos de consenso en redesDetección de nodos tramposos en procesos de consenso en redes
Detección de nodos tramposos en procesos de consenso en redes
Miguel Rebollo
 
La hora del código: ApS para fomentar el pensamiento computacional
La hora del código: ApS para fomentar el pensamiento computacionalLa hora del código: ApS para fomentar el pensamiento computacional
La hora del código: ApS para fomentar el pensamiento computacional
Miguel Rebollo
 
Procesos de enseñanza-aprendizaje en red
Procesos de enseñanza-aprendizaje en redProcesos de enseñanza-aprendizaje en red
Procesos de enseñanza-aprendizaje en red
Miguel Rebollo
 
desarrollo de competencias a través de narrativas transmedia
desarrollo de competencias a través de narrativas transmediadesarrollo de competencias a través de narrativas transmedia
desarrollo de competencias a través de narrativas transmedia
Miguel Rebollo
 
Distributed Group Analytical Hierarchical Process by Consensus
 Distributed Group Analytical Hierarchical Process by Consensus Distributed Group Analytical Hierarchical Process by Consensus
Distributed Group Analytical Hierarchical Process by Consensus
Miguel Rebollo
 
Análisis de ciudades a través de su actividad en redes sociales
Análisis de ciudades a través de su actividad en redes socialesAnálisis de ciudades a través de su actividad en redes sociales
Análisis de ciudades a través de su actividad en redes sociales
Miguel Rebollo
 
Análisis de datos en redes sociales
Análisis de datos en redes socialesAnálisis de datos en redes sociales
Análisis de datos en redes sociales
Miguel Rebollo
 
The multigent Layer for CALMeD SURF
The multigent Layer for CALMeD SURFThe multigent Layer for CALMeD SURF
The multigent Layer for CALMeD SURF
Miguel Rebollo
 
Narrativa transmedia en el aula
Narrativa transmedia en el aulaNarrativa transmedia en el aula
Narrativa transmedia en el aula
Miguel Rebollo
 
Using geo-tagged sentiment to better understand social interactions
 Using geo-tagged sentiment to better understand social interactions Using geo-tagged sentiment to better understand social interactions
Using geo-tagged sentiment to better understand social interactions
Miguel Rebollo
 

More from Miguel Rebollo (20)

IA en entornos rurales aplicada a la viticultura
IA en entornos rurales aplicada a la viticulturaIA en entornos rurales aplicada a la viticultura
IA en entornos rurales aplicada a la viticultura
 
Inteligencia artificial para una transformación inteligente
Inteligencia artificial para una transformación inteligenteInteligencia artificial para una transformación inteligente
Inteligencia artificial para una transformación inteligente
 
GTG-CoL: A Decentralized Federated Learning Based on Consensus for Dynamic N...
 GTG-CoL: A Decentralized Federated Learning Based on Consensus for Dynamic N... GTG-CoL: A Decentralized Federated Learning Based on Consensus for Dynamic N...
GTG-CoL: A Decentralized Federated Learning Based on Consensus for Dynamic N...
 
Co-Learning: Consensus-based Learning for Multi-Agent Systems
 Co-Learning: Consensus-based Learning for Multi-Agent Systems Co-Learning: Consensus-based Learning for Multi-Agent Systems
Co-Learning: Consensus-based Learning for Multi-Agent Systems
 
Análisis de la red de autores de ciencia ficción de Clarkesworld
Análisis de la red de autores de ciencia ficción de ClarkesworldAnálisis de la red de autores de ciencia ficción de Clarkesworld
Análisis de la red de autores de ciencia ficción de Clarkesworld
 
Y sin embargo... se mueve. Dinámica de las redes complejas
Y sin embargo... se mueve. Dinámica de las redes complejasY sin embargo... se mueve. Dinámica de las redes complejas
Y sin embargo... se mueve. Dinámica de las redes complejas
 
Exámenes en grupo y pruebas de corrección como alternativas a la evaluación
Exámenes en grupo y pruebas de corrección como alternativas a la evaluaciónExámenes en grupo y pruebas de corrección como alternativas a la evaluación
Exámenes en grupo y pruebas de corrección como alternativas a la evaluación
 
Gamification. Key Concepts
Gamification. Key ConceptsGamification. Key Concepts
Gamification. Key Concepts
 
Using Distributed Risk Maps by Consensus as a Complement to Contact Tracing Apps
Using Distributed Risk Maps by Consensus as a Complement to Contact Tracing AppsUsing Distributed Risk Maps by Consensus as a Complement to Contact Tracing Apps
Using Distributed Risk Maps by Consensus as a Complement to Contact Tracing Apps
 
Distributed Ledger and Robust Consensus for Agreements
Distributed Ledger and Robust Consensus for AgreementsDistributed Ledger and Robust Consensus for Agreements
Distributed Ledger and Robust Consensus for Agreements
 
Detección de nodos tramposos en procesos de consenso en redes
Detección de nodos tramposos en procesos de consenso en redesDetección de nodos tramposos en procesos de consenso en redes
Detección de nodos tramposos en procesos de consenso en redes
 
La hora del código: ApS para fomentar el pensamiento computacional
La hora del código: ApS para fomentar el pensamiento computacionalLa hora del código: ApS para fomentar el pensamiento computacional
La hora del código: ApS para fomentar el pensamiento computacional
 
Procesos de enseñanza-aprendizaje en red
Procesos de enseñanza-aprendizaje en redProcesos de enseñanza-aprendizaje en red
Procesos de enseñanza-aprendizaje en red
 
desarrollo de competencias a través de narrativas transmedia
desarrollo de competencias a través de narrativas transmediadesarrollo de competencias a través de narrativas transmedia
desarrollo de competencias a través de narrativas transmedia
 
Distributed Group Analytical Hierarchical Process by Consensus
 Distributed Group Analytical Hierarchical Process by Consensus Distributed Group Analytical Hierarchical Process by Consensus
Distributed Group Analytical Hierarchical Process by Consensus
 
Análisis de ciudades a través de su actividad en redes sociales
Análisis de ciudades a través de su actividad en redes socialesAnálisis de ciudades a través de su actividad en redes sociales
Análisis de ciudades a través de su actividad en redes sociales
 
Análisis de datos en redes sociales
Análisis de datos en redes socialesAnálisis de datos en redes sociales
Análisis de datos en redes sociales
 
The multigent Layer for CALMeD SURF
The multigent Layer for CALMeD SURFThe multigent Layer for CALMeD SURF
The multigent Layer for CALMeD SURF
 
Narrativa transmedia en el aula
Narrativa transmedia en el aulaNarrativa transmedia en el aula
Narrativa transmedia en el aula
 
Using geo-tagged sentiment to better understand social interactions
 Using geo-tagged sentiment to better understand social interactions Using geo-tagged sentiment to better understand social interactions
Using geo-tagged sentiment to better understand social interactions
 

Recently uploaded

Nutraceutical market, scope and growth: Herbal drug technology
Nutraceutical market, scope and growth: Herbal drug technologyNutraceutical market, scope and growth: Herbal drug technology
Nutraceutical market, scope and growth: Herbal drug technology
Lokesh Patil
 
Cancer cell metabolism: special Reference to Lactate Pathway
Cancer cell metabolism: special Reference to Lactate PathwayCancer cell metabolism: special Reference to Lactate Pathway
Cancer cell metabolism: special Reference to Lactate Pathway
AADYARAJPANDEY1
 
plant biotechnology Lecture note ppt.pptx
plant biotechnology Lecture note ppt.pptxplant biotechnology Lecture note ppt.pptx
plant biotechnology Lecture note ppt.pptx
yusufzako14
 
Richard's entangled aventures in wonderland
Richard's entangled aventures in wonderlandRichard's entangled aventures in wonderland
Richard's entangled aventures in wonderland
Richard Gill
 
In silico drugs analogue design: novobiocin analogues.pptx
In silico drugs analogue design: novobiocin analogues.pptxIn silico drugs analogue design: novobiocin analogues.pptx
In silico drugs analogue design: novobiocin analogues.pptx
AlaminAfendy1
 
Large scale production of streptomycin.pptx
Large scale production of streptomycin.pptxLarge scale production of streptomycin.pptx
Large scale production of streptomycin.pptx
Cherry
 
Comparative structure of adrenal gland in vertebrates
Comparative structure of adrenal gland in vertebratesComparative structure of adrenal gland in vertebrates
Comparative structure of adrenal gland in vertebrates
sachin783648
 
NuGOweek 2024 Ghent - programme - final version
NuGOweek 2024 Ghent - programme - final versionNuGOweek 2024 Ghent - programme - final version
NuGOweek 2024 Ghent - programme - final version
pablovgd
 
Astronomy Update- Curiosity’s exploration of Mars _ Local Briefs _ leadertele...
Astronomy Update- Curiosity’s exploration of Mars _ Local Briefs _ leadertele...Astronomy Update- Curiosity’s exploration of Mars _ Local Briefs _ leadertele...
Astronomy Update- Curiosity’s exploration of Mars _ Local Briefs _ leadertele...
NathanBaughman3
 
THE IMPORTANCE OF MARTIAN ATMOSPHERE SAMPLE RETURN.
THE IMPORTANCE OF MARTIAN ATMOSPHERE SAMPLE RETURN.THE IMPORTANCE OF MARTIAN ATMOSPHERE SAMPLE RETURN.
THE IMPORTANCE OF MARTIAN ATMOSPHERE SAMPLE RETURN.
Sérgio Sacani
 
EY - Supply Chain Services 2018_template.pptx
EY - Supply Chain Services 2018_template.pptxEY - Supply Chain Services 2018_template.pptx
EY - Supply Chain Services 2018_template.pptx
AlguinaldoKong
 
Orion Air Quality Monitoring Systems - CWS
Orion Air Quality Monitoring Systems - CWSOrion Air Quality Monitoring Systems - CWS
Orion Air Quality Monitoring Systems - CWS
Columbia Weather Systems
 
FAIR & AI Ready KGs for Explainable Predictions
FAIR & AI Ready KGs for Explainable PredictionsFAIR & AI Ready KGs for Explainable Predictions
FAIR & AI Ready KGs for Explainable Predictions
Michel Dumontier
 
insect morphology and physiology of insect
insect morphology and physiology of insectinsect morphology and physiology of insect
insect morphology and physiology of insect
anitaento25
 
Hemoglobin metabolism_pathophysiology.pptx
Hemoglobin metabolism_pathophysiology.pptxHemoglobin metabolism_pathophysiology.pptx
Hemoglobin metabolism_pathophysiology.pptx
muralinath2
 
The ASGCT Annual Meeting was packed with exciting progress in the field advan...
The ASGCT Annual Meeting was packed with exciting progress in the field advan...The ASGCT Annual Meeting was packed with exciting progress in the field advan...
The ASGCT Annual Meeting was packed with exciting progress in the field advan...
Health Advances
 
Multi-source connectivity as the driver of solar wind variability in the heli...
Multi-source connectivity as the driver of solar wind variability in the heli...Multi-source connectivity as the driver of solar wind variability in the heli...
Multi-source connectivity as the driver of solar wind variability in the heli...
Sérgio Sacani
 
Anemia_ different types_causes_ conditions
Anemia_ different types_causes_ conditionsAnemia_ different types_causes_ conditions
Anemia_ different types_causes_ conditions
muralinath2
 
platelets- lifespan -Clot retraction-disorders.pptx
platelets- lifespan -Clot retraction-disorders.pptxplatelets- lifespan -Clot retraction-disorders.pptx
platelets- lifespan -Clot retraction-disorders.pptx
muralinath2
 
Body fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptx
Body fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptxBody fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptx
Body fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptx
muralinath2
 

Recently uploaded (20)

Nutraceutical market, scope and growth: Herbal drug technology
Nutraceutical market, scope and growth: Herbal drug technologyNutraceutical market, scope and growth: Herbal drug technology
Nutraceutical market, scope and growth: Herbal drug technology
 
Cancer cell metabolism: special Reference to Lactate Pathway
Cancer cell metabolism: special Reference to Lactate PathwayCancer cell metabolism: special Reference to Lactate Pathway
Cancer cell metabolism: special Reference to Lactate Pathway
 
plant biotechnology Lecture note ppt.pptx
plant biotechnology Lecture note ppt.pptxplant biotechnology Lecture note ppt.pptx
plant biotechnology Lecture note ppt.pptx
 
Richard's entangled aventures in wonderland
Richard's entangled aventures in wonderlandRichard's entangled aventures in wonderland
Richard's entangled aventures in wonderland
 
In silico drugs analogue design: novobiocin analogues.pptx
In silico drugs analogue design: novobiocin analogues.pptxIn silico drugs analogue design: novobiocin analogues.pptx
In silico drugs analogue design: novobiocin analogues.pptx
 
Large scale production of streptomycin.pptx
Large scale production of streptomycin.pptxLarge scale production of streptomycin.pptx
Large scale production of streptomycin.pptx
 
Comparative structure of adrenal gland in vertebrates
Comparative structure of adrenal gland in vertebratesComparative structure of adrenal gland in vertebrates
Comparative structure of adrenal gland in vertebrates
 
NuGOweek 2024 Ghent - programme - final version
NuGOweek 2024 Ghent - programme - final versionNuGOweek 2024 Ghent - programme - final version
NuGOweek 2024 Ghent - programme - final version
 
Astronomy Update- Curiosity’s exploration of Mars _ Local Briefs _ leadertele...
Astronomy Update- Curiosity’s exploration of Mars _ Local Briefs _ leadertele...Astronomy Update- Curiosity’s exploration of Mars _ Local Briefs _ leadertele...
Astronomy Update- Curiosity’s exploration of Mars _ Local Briefs _ leadertele...
 
THE IMPORTANCE OF MARTIAN ATMOSPHERE SAMPLE RETURN.
THE IMPORTANCE OF MARTIAN ATMOSPHERE SAMPLE RETURN.THE IMPORTANCE OF MARTIAN ATMOSPHERE SAMPLE RETURN.
THE IMPORTANCE OF MARTIAN ATMOSPHERE SAMPLE RETURN.
 
EY - Supply Chain Services 2018_template.pptx
EY - Supply Chain Services 2018_template.pptxEY - Supply Chain Services 2018_template.pptx
EY - Supply Chain Services 2018_template.pptx
 
Orion Air Quality Monitoring Systems - CWS
Orion Air Quality Monitoring Systems - CWSOrion Air Quality Monitoring Systems - CWS
Orion Air Quality Monitoring Systems - CWS
 
FAIR & AI Ready KGs for Explainable Predictions
FAIR & AI Ready KGs for Explainable PredictionsFAIR & AI Ready KGs for Explainable Predictions
FAIR & AI Ready KGs for Explainable Predictions
 
insect morphology and physiology of insect
insect morphology and physiology of insectinsect morphology and physiology of insect
insect morphology and physiology of insect
 
Hemoglobin metabolism_pathophysiology.pptx
Hemoglobin metabolism_pathophysiology.pptxHemoglobin metabolism_pathophysiology.pptx
Hemoglobin metabolism_pathophysiology.pptx
 
The ASGCT Annual Meeting was packed with exciting progress in the field advan...
The ASGCT Annual Meeting was packed with exciting progress in the field advan...The ASGCT Annual Meeting was packed with exciting progress in the field advan...
The ASGCT Annual Meeting was packed with exciting progress in the field advan...
 
Multi-source connectivity as the driver of solar wind variability in the heli...
Multi-source connectivity as the driver of solar wind variability in the heli...Multi-source connectivity as the driver of solar wind variability in the heli...
Multi-source connectivity as the driver of solar wind variability in the heli...
 
Anemia_ different types_causes_ conditions
Anemia_ different types_causes_ conditionsAnemia_ different types_causes_ conditions
Anemia_ different types_causes_ conditions
 
platelets- lifespan -Clot retraction-disorders.pptx
platelets- lifespan -Clot retraction-disorders.pptxplatelets- lifespan -Clot retraction-disorders.pptx
platelets- lifespan -Clot retraction-disorders.pptx
 
Body fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptx
Body fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptxBody fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptx
Body fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptx
 

Analysis of the Evolution of Events on Online Social Networks

  • 1. Introduction Results. Event analysis Discussion Conclusions Analysis of the Evolution of Events on Online Social Networks E. del Val, M. Rebollo and V. Botti Grupo Tec. Inform.-Inteligencia Artificial Universitat Politècnica de València CSS 2014 @mrebollo UPV Analysis of the Evolution of Events on Online Social Networks
  • 2. Introduction Results. Event analysis Discussion Conclusions Problem Analysis of user behavior How user interactions evolve in a social network associated to the realization of a scheduled event in the real world. 4 types of events are considered TV shows socio-political conferences keynotes @mrebollo UPV Analysis of the Evolution of Events on Online Social Networks
  • 3. Introduction Results. Event analysis Discussion Conclusions The Hypothesis There are significative differences in the behavior of the participants in each type of event @mrebollo UPV Analysis of the Evolution of Events on Online Social Networks
  • 4. Introduction Results. Event analysis Discussion Conclusions Data set twits containing the hashtag of the event are retrieved interaction-based network: mentions, replies and retweets focus on scheduled events temporally annotated network (nodes and links) empirical analysis @mrebollo UPV Analysis of the Evolution of Events on Online Social Networks
  • 5. Introduction Results. Event analysis Discussion Conclusions Events TV shows La voz Topchef BreakingBad OperacionPalace Keynotes applekeynote nuevosiphone innovationreinvented (Nokia) Socio-political lomce viacatalana EU elections debate Conferences TEDValencia seo4seos Twitter awards 2013 InternetOfThings forum CW’13 (web conference) @mrebollo UPV Analysis of the Evolution of Events on Online Social Networks
  • 6. Introduction Results. Event analysis Discussion Conclusions Event characterization Event N E clust. d path comp. k m GC %sl #lomce #24O 61,653 97,570 0.07 27 6.93 8,088 1.58 0.73 49,164 10.80 #via 41,166 76,094 0.07 23 8.28 8,705 1.85 0.56 30,745 12.19 catalana #topchef12 26,044 27,155 0.05 25 8.74 10,689 1.04 0.66 12,794 12.29 #lavoz 45,914 39,891 0.07 9 2.11 19,398 0.87 0.81 17,941 6.95 #breakingbad 151,473 120,661 0.05 13 3.24 67,060 0.80 0.72 71,130 14.26 #operacion 107,606 195,470 0.08 23 8.26 19,504 1.82 0.49 85,768 15.06 Palace #apple 3,367 1,729 0.04 4 1.27 1,827 0.51 0.93 700 1.53 keynote #nuevos 9,509 10,600 0.05 9 2.09 1,227 1.12 0.62 7,799 6.47 iPhone #innovation 110 95 0.04 3 1.34 32 0.86 0.83 26 10.00 reinvented #IoTWF 4,150 17,545 0.22 9 3.96 330 4.23 0.42 3,680 30.83 #cw13 1,051 2,608 0.20 9 3.90 60 2.48 0.56 966 19.76 #seo4seos 367 1,474 0.35 6 2.91 16 4.02 0.30 347 31.07 #tedx 325 843 0.17 8 3.60 45 2.59 0.32 276 8.60 valencia @mrebollo UPV Analysis of the Evolution of Events on Online Social Networks
  • 7. Introduction Results. Event analysis Discussion Conclusions Message type tv: linear, global, during soc: linear, inter., always keyn: global, before conf: linear, inter., during 45000 40000 35000 30000 25000 20000 15000 10000 5000 0 0 50 100 150 200 250 300 350 num tweets snapshot global retweets mentions replyTo (a) TV show: #topchef12. 60000 50000 40000 30000 20000 10000 0 0 50 100 150 200 250 300 350 num tweets snapshot global retweets mentions replyTo (b) Socio-political: #viacatalana 6000 5000 4000 3000 2000 1000 0 0 50 100 150 200 250 300 350 num tweets snapshot global retweets mentions replyTo (c) Keynote: #applekeynote 1000 800 600 400 200 0 0 100 200 300 400 500 600 700 num tweets snapshot global retweets mentions replyTo (d) Conference: #tedxValencia Figure 2: Evolution of the number of global and individual messages (mentions, retweets, and reply to) in different type of events. @mrebollo UPV Analysis of the Evolution of Events on Online Social Networks 9
  • 8. Introduction Results. Event analysis Discussion Conclusions Network size (links and nodes) tv: always, similar soc: always, ""links keyn: before, ""links conf: but after, ""links 30000 25000 20000 15000 10000 5000 0 0 50 100 150 200 250 300 350 num links or nodes snapshot links nodes (a) TV show: #topchef12. 80000 70000 60000 50000 40000 30000 20000 10000 0 0 50 100 150 200 250 300 350 num links or nodes snapshot links nodes (b) Socio-political: #viacatalana. 3500 3000 2500 2000 1500 1000 500 0 0 50 100 150 200 250 300 350 num links or nodes snapshot links nodes (c) Keynote: #applekeynote. 900 800 700 600 500 400 300 200 100 0 0 100 200 300 400 500 600 700 num links or nodes snapshot links nodes (d) Conference: #tedxValencia. Figure 3: Evolution of the number of nodes and links in different type of events. the number of nodes and links increases moderately. People in the analyzed events prefer to talk and interact before the event rather than during the keynote. In the analyzed conference networks, the number of nodes grows rapidly before the event starts (see Figure 3d). Then, during the event, there is also an important increase in the number of nodes. Towards the end of the event as well as after the event, the number of nodes remains almost constant. If the conference consists on two or three days, during the first day is when a most significant increase in the number of new nodes occurs. The number of links evolves similarly as the nodes. However, the increase in the number of interactions is produced at a higher rate. This means that assistants to a conference are more social and interact with other assistants. This behavior is similar to behavior of participants in socio-political networks. @mrebollo UPV Analysis of the Evolution of Events on Online Social Networks
  • 9. Introduction Results. Event analysis Discussion Conclusions Symmetric links tv: low, decreasing soc: low, constant keyn: lowest conf: tipically high, constant 40 35 30 25 20 15 10 5 0 % of symmetric links 0 50 100 150 200 250 300 350 symmetric links snapshot (a) TV show: #topchef12. 40 35 30 25 20 15 10 5 0 % of symmetric links 0 50 100 150 200 250 300 350 symmetric links snapshot (b) Socio-political: #viacatalana. 40 35 30 25 20 15 10 5 0 % of symmetric links 0 50 100 150 200 250 300 350 symmetric links snapshot (c) Keynote: #applekeynote. 40 35 30 25 20 15 10 5 0 % of symmetric links 0 100 200 300 400 500 600 700 symmetric links snapshot (d) Conference: #tedxValencia. Figure 4: Evolution of the number of symmetric links in different type of events. @mrebollo UPV Analysis of the Evolution of Events on Online Social Networks 12
  • 10. Introduction Results. Event analysis Discussion Conclusions Cummulative degree distrib. and CCDF @mrebollo UPV Analysis of the Evolution of Events on Online Social Networks
  • 11. Introduction Results. Event analysis Discussion Conclusions Path length and diameter all: grows before and remains constant non significative differences 30 25 20 15 10 5 0 path Length 0 50 100 150 200 250 300 350 num steps timeStep diameter (a) TV show: #topchef12. 30 25 20 15 10 5 0 path Length 0 50 100 150 200 250 300 350 num steps timeStep diameter (b) Socio-political: #viacatalana. 4 3.5 3 2.5 2 1.5 1 path Length 0 50 100 150 200 250 300 350 num steps timeStep diameter (c) Keynote: #applekeynote. 9 8 7 6 5 4 3 2 1 path Length 0 100 200 300 400 500 600 700 num steps timeStep diameter (d) Conference: #tedxValencia. Figure 6: Evolution of the average path length and diameter in different type of events. @mrebollo UPV Analysis of the Evolution of Events on Online Social Networks 15
  • 12. Introduction Results. Event analysis Discussion Conclusions Clustering not significative in the evolution differences in the values ("conf, ## keyn) 0.4 0.35 0.3 0.25 0.2 0.15 0.1 0.05 0 clustering dynamics 0 50 100 150 200 250 300 350 Clustering Degree timeStep (a) TV show: #topchef12. 0.4 0.35 0.3 0.25 0.2 0.15 0.1 0.05 0 clustering dynamics 0 50 100 150 200 250 300 350 Clustering Degree timeStep (b) Socio-political: #viacatalana. 0.4 0.35 0.3 0.25 0.2 0.15 0.1 0.05 0 clustering dynamics 0 50 100 150 200 250 300 350 Clustering Degree timeStep (c) Keynote: #applekeynote. 0.4 0.35 0.3 0.25 0.2 0.15 0.1 0.05 0 clustering dynamics 0 100 200 300 400 500 600 700 Clustering Degree timeStep (d) Conference: #tedxValencia. Figure 7: Evolution of the average clustering in different type of events. @mrebollo UPV Analysis of the Evolution of Events on Online Social Networks 16
  • 13. Introduction Results. Event analysis Discussion Conclusions Nodes in the giant component all: created before the event tv and keyn: low soc and conf: high 100 80 60 40 20 0 % of nodes 0 50 100 150 200 250 300 350 % of nodes that are in the giant component timeStep (a) TV show: #topchef12. 100 80 60 40 20 0 % of nodes 0 50 100 150 200 250 300 350 % of nodes that are in the giant component timeStep (b) Socio-political: #viacatalana. 100 80 60 40 20 0 % of nodes 0 50 100 150 200 250 300 350 % of nodes that are in the giant component timeStep (c) Keynote: #applekeynote. 100 80 60 40 20 0 % of nodes 0 100 200 300 400 500 600 700 % of nodes that are in the giant component timeStep (d) Conference: #tedxValencia. Figure 8: Evolution of the % of nodes that are part of the giant component in different type of events. @mrebollo UPV Analysis of the Evolution of Events on Online Social Networks 17
  • 14. Introduction Results. Event analysis Discussion Conclusions Betweenness tv: official + celebrities soc: politics, journalists, bloggers keyn: media, tech sites, bloggers conf: official + speakers                             (a) TV show: #topchef12.                              (b) Socio-political: #viacatalana.                                (c) Keynote: #applekeynote.                              (d) Conference: #tedxValencia. Figure 9: Evolution of the betweenness of the ten nodes with the highest betweenness value in different type of events. The nodes with the highest betweenness value in the analyzed keynote networks are the nodes that represent media, technological web pages, and bloggers. In general, the value of betweenness of these nodes starts increasing before the event and after the event (see Figure 9c). However, during the event, the values of betweenness remain constant since there are not a high number of interactions (new links) between nodes. There is a big difference between the nodes that represent media or web pages and the rest of the nodes that represent bloggers or users. In the analyzed conference networks, the nodes with the highest betweenness are official accounts and speakers. In general, the official account has the highest betweenness value with respect the betweenness of the speakers (see Figure 9d). During the event, the betweenness of the official account increases at a higher rate than the speakers account. Among the nodes that represent the speakers there is also a difference between those that participate in the first sessions and the speakers that participate in later sessions. The betweenness of the speakers that participate in the first sessions increases from the beginning. However, the betweenness of the speakers that participate in later sessions is initially almost constant and starts to increase once the speaker participates in the conference. After the event the betweenness of all nodes remains almost constant. @mrebollo UPV Analysis of the Evolution of Events on Online Social Networks
  • 15. Introduction Results. Event analysis Discussion Conclusions Indegree and outdegree tv, soc and keyn: indegree same as betweenness; outdegree anonymous conf: balanced                               (a) TV show: #topchef12. Indegree                                (b) TV show: #topchef12. Outdegree                            (c) Socio-political: #viacatalana. Indegree                              (d) Socio-political: #viacatalana. Outdegree                              (e) Keynote: #applekeynote. Indegree                                 (f) Keynote: #applekeynote. Outdegree                            (g) Conference: #tedxValencia. Indegree                             (h) Conference: #tedxValencia. Outdegree 21 Figure 10: Evolution of the indegree and outdegree of the ten nodes with the highest indegree and outdegree value in different type of events. @mrebollo UPV Analysis of the Evolution of Events on Online Social Networks
  • 16. Introduction Results. Event analysis Discussion Conclusions Eigenvector "" heterogeneous (even in the same event type) not significative                           (a) TV show: #topchef12.                           (b) Socio-political: #viacatalana.                              (c) Keynote: #applekeynote.                           (d) Conference: #tedxValencia. Figure 11: Evolution of the eigenvector of the ten nodes with the highest eigenvector value in different type of events. connection join the network and the eigenvector of the speakers decreases steadily. In contrast, the speakers that participate in the event later on have an eigenvector that increases smoothly before their participation in the event. Then, when the speakers participate in the event, their eigenvector increases sharply. This means that other nodes with a high degree of connection establish a connection with the speakers. After this increase, the eigenvector centrality of the last speakers remains almost constant or there is a small decrease. When the event is going to finish, the eigenvector of all the nodes remains almost constant. 6. Discussion After the analysis of the networks, we observed that the networks generated from the Twitter events can be @mrebollo classified in two main groups based on the type of interactions between users. One group consists of the TV UPV Analysis of the Evolution of Events on Online Social Networks show and keynote networks. The other group consists of the socio-political and conference networks. In the group of TV show and keynote networks, users tend to participate in the event through global mes-sages. The majority of interactions are unidirectional from unknown users to official accounts or celebrities.
  • 17. Introduction Results. Event analysis Discussion Conclusions Discussion two clearly differenced types TV shows and keynotes global, undirectional messages asymmetric: celebrities - annonymous low clustering and long pathes TV: after & before; keyn: during socio-political and conferences real communication among participants higher symmetry, reciprocity conf: official account more participative @mrebollo UPV Analysis of the Evolution of Events on Online Social Networks
  • 18. Introduction Results. Event analysis Discussion Conclusions Conclusions Conclusions official event account barely influences communities created around ’persons of interest’ giant component created before event 2 groups clearly differencied significant differences among the 4 groups Future work follow user activity to complete de information include decay in the links include specific temporal measures; multiplex structure create models for events and user profiles @mrebollo UPV Analysis of the Evolution of Events on Online Social Networks