Modeling Communities in Information Systems: Informal Learning Communities in Social Media
1. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
1/36
TeLLNet
This work is licensed under a Creative Commons Attribution-ShareAlike 3.0 Unported License.
M. Sc. Zinayida Kensche (née Petrushyna)
Doctoral Thesis Defense
Chair of Information Systems and Databases
RWTH Aachen University
Aachen
November 17, 2015
Modeling Communities in Information Systems:
Informal Learning Communities in Social Media
2. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
2/36
TeLLNet
Outline
Motivation and Research Questions
Background and Context of Informal Learning
Continuous Support of Community Life Cycle
Test cases
– Modeling Informal Learning Communities in
Learning Forums
– Competence Management in Lifelong Learning Communities
Conclusion and Outlook
3. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
3/36
TeLLNet
Formal learning communities are students in lectures
Informal learning communities are self-organized
Stakeholders care about their communities:
– What are insights of informal learning communities?
– Their success and failures?
– Can communities learn from other communities?
– How do communities evolve?
Motivation
Motivation
Background
and context
Methodology
Conclusions
and Outlook
Technical
Contribution
Test Cases
4. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
4/36
TeLLNet
Social Media Usage for Informal Learning
Learning Analytics Conceptual Modeling
Formal learning:
a MOOC
Informal learning:
forums, blogs,
mailing lists,
chats,
social network sites
Motivation
Background
and context
Methodology
Conclusions
and Outlook
Technical
Contribution
Test Cases
5. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
5/36
TeLLNet
Research Questions
Connecting advanced computer science tools and learning theories –
the interdisciplinary character of the work
Suh & Lee, 2006, Kleanthous & Dimitrova, 2007, 2010, Abel et al., 2011
Creating stereotype models and selecting suitable ones that describe
community situations, needs, types, and future positions
Zhang & Taniru, 2005, Li et al. 2008, Hilts & Yu, 2011, Fereira & Silva, 2012
Advanced computer science tools support communities by providing results of
analytical investigation and estimation of community needs
Wolpers et al., 2007, Kodinger et al., 2008, Upton & Kay, 2009, Dascalu et al., 2010,
Scheffel et al. 2011, Karam et al., 2012, Verbert et al., 2012, Rabbany k. et al., 2012
Motivation
Background
and context
Methodology
Conclusions
and Outlook
Technical
Contribution
Test Cases
6. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
6/36
TeLLNet
Networked learning & community of practice: learning in
collaboration Wenger, 1998, Dillenbourg, 1999, Stahl, 2006
Learning Theories Recapitulation
1934 1954 197119721973 1980 1986 1998
Social constructivism: social influence on learning Vygotsky, 1934/1986
Social learning/cognitive theory: society is pivotal for a learner Bandura, 1971, 1986
1999 2006
Cognitivism: individual style of learning
Pask and Scott, 1972
Behaviorism: learning processes are guided
interactions are shaped, Skinner, 1954
Cognitive constructivism: learning by
discovery Piaget, 1973, Papert, 1980
Teaching machine
Lack of
social
aspects
of
learning
Cognitive
processes
Assimilating
new and
existing
knowledge
Motivation
Background
and context
Methodology
Conclusions
and Outlook
Technical
Contribution
Test Cases
7. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
7/36
TeLLNet
Community of Practice and Technology
Digital Media/
Community
Information Systems
Web 2.0 Processes/
i* Models/ Strategies
(Cross-media Analysis)
Members
(Social Network Analysis,
Community Detection &
Evolution)
Network of Artifacts
(Emotional Analysis, Intent Analysis,
Information Retrieval. Social Network
Analysis)
Network of Members
Communities of practice
Media Networks
Communities of Practice: collaborating, sharing same goals and interests
Wenger, 1998
Data management Klamma, 2010
Community analytics Yu, 2009
Conceptual modeling
Klamma, 2013
correspond to CoP dimensions and
actors in media networks
Motivation
Background
and context
Methodology
Conclusions
and Outlook
Technical
Contribution
Test Cases
8. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
8/36
TeLLNet
Overview of Research Answers
Systematic workflow for overall approach Petrushyna et al., 2014
Ground laying model for informal learning communities in digital
media Petrushyna et al., 2010
Repository of model stereotypes Petrushyna et al., 2014
Simulation approach for refining online informal learning
community models
Tool set for modeling, monitoring and analyzing of informal learning
communities in social media Petrushyna & Klamma, 2008, Klamma & Petrushyna,
2010, Krenge et al., 2011, Song et al., 2011, Petrushyna et al., 2014, Petrushyna et al., 2014a,
Petrushyna et al., 2015
RQ1
RQ2
RQ2
RQ2
RQ3
Motivation
Background
and context
Methodology
Conclusions
and Outlook
Technical
Contribution
Test Cases
9. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
9/36
TeLLNet
Technical Contributions
The metamodel of informal learning communities in digital media
The i*-REST service for modeling communities in i* Petrushyna et al., 2014
Professional and social competence modeling using social network
analysis Song et al., 2011
The general agent-based model of informal learning communities
Community stereotype model repository Petrushyna et al., 2014
Mapping of i* models to Java based agents
Simulations of agent-based models of learning communities
A design of data cube appropriate for heterogenous data
storage and rapid query processing Klamma and Petrushyna, 2008
The TargETLy service for community analysis Petrushyna et al., 2015,
Krenge et al., 2011, Petrushyna et al., 2011
Implementation of community detection/evolution algorithms for
large networks in distributive environment
The competence management support framework for lifelong
learning communities Song et al., 2011
Estimation of learning quality using community analysis Pham et al., 2012
Modeling
Refinement
Monitoring
Analysis
Motivation
Background
and context
Methodology
Conclusions
and Outlook
Technical
Contribution
Test Cases
10. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
10/36
TeLLNet
Workflow of Community Learning Analytics
Continuous
requirements
Maintenance of stored community digital traces
Defining user patterns, emotions, intents, concepts and
topics of interest
Detecting communities and their evolution
Communities are represented by stereotype models
Smith and Kollock, 1999, Cheung et al., 2005, Madanmohan and Siddhesh, 2004,
Niegemann and Domagk , 2005, Fisher et al., 2006, Turner et al., 2005
Models reveal community requirements and insights
Stakeholders maintain communities operating
suitable models
Simulations used to identify possible community changes
Jarke et al., 2008
Petrushyna et al., 2014 RQ1
Modeling
Refinement
Monitoring
Analysis
Motivation
Background
and context
Methodology
Conclusions
and Outlook
Technical
Contribution
Test Cases
11. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
11/36
TeLLNet
Learning
resource
Learning
goal
Acceptance
Support
learning
process
Learner A Expert
Community Learner
Modeling: i* Modeling Approach for Informal
Learning Community Modeling
RQ2
Dependency
resource
Goal
Softgoal
Task
Agent Role
Depender
Agent
Dependee
Agent
+ models can be
extended to describe
the rationale of agents
+ point out
dependencies between
human and non-human
agents
+ emphasize agents,
their types and roles
+ indicate intentions in
social networks
+ models can be created
using XML-based format
- too abstract
- before applying i* modeling training is required
Motivation
Background
and context
Methodology
Conclusions
and Outlook
Technical
Contribution
Test Cases
12. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
12/36
TeLLNet
Modeling: A General Learning Community Model
RQ2
Learner
Community
Learner
A
composes
interacts
Learner
B
creates
space for
knowledge
sharing
rules
and
policies
limitations
learns
from
Resource
dependency
Agent
Dependee
Depender
Task
dependency
Agent
Goal
dependency
Mutual engagement Shared repertoire Joint enterprises
Motivation
Background
and context
Methodology
Conclusions
and Outlook
Technical
Contribution
Test Cases
ProcessProcess
ArtifactArtifact
initializes
D
D
MediumMedium hostsD D
consists
of
D
D
influences
D
D
13. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
13/36
TeLLNet
Resource
dependency
Agent
Dependee
Depender
Task
dependency
Agent
Goal
dependency
Stereotypes of Learning Communities
Communities can be represented by stereotype models
Smith and Kollock, 1999, Madanmohan and Siddhesh, 2004, Cheung et al., 2005, Niegemann and Domagk , 2005,
Turner et al., 2005, Fisher et al., 2006
RQ2
Teacher-oriented
Learner-oriented
Lifelong learners-oriented
Question-answer
Dispute
Innovative
Culture-sensitive
At workplace
Community of interest
Motivation
Background
and context
Methodology
Conclusions
and Outlook
Technical
Contribution
Test Cases
14. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
14/36
TeLLNet
Refinement: A General Agent-based Model of
An Informal Learning Community in Media
Society 𝑆𝑜𝑐 = 𝐴, 𝐴𝑐𝑡
𝐴 = {𝐴1 … 𝐴 𝑛} is a set of agents
𝐴𝑐𝑡 is a set of predefined actions of agents 𝐴
𝐴𝑟𝑡𝑖𝑓𝑎𝑐𝑡𝑠 𝑡 = 𝐴𝑟𝑡𝑖𝑓𝑎𝑐𝑡1 … 𝐴𝑟𝑡𝑖𝑓𝑎𝑐𝑡 𝑘 𝑡
are created by agents A
with 𝐴𝑐𝑡 at 𝑡
𝑅 𝑡 ∈ 𝐴 × 𝐴 × ℝ+ are social relations, where 𝑡 is a time point
𝐴
𝜃(𝑡)
𝐶 𝑡, where 𝐶 𝑡 = 𝐶1 … 𝐶 𝑚 𝑡
⊆ 𝐶 , 𝐶 𝑡 is a set of communities
𝑀𝑒𝑑𝑖𝑎 = {𝑀𝑒𝑑𝑖𝑢𝑚1, … 𝑀𝑒𝑑𝑖𝑢𝑚 𝑟}, where
𝐴𝑟𝑡𝑖𝑓𝑎𝑐𝑡𝑠 𝑡
𝜗(𝑡)
𝑀𝑒𝑑𝑖𝑢𝑚𝑖
𝑆 = 𝑆1 … 𝑆 𝑑 is a set of strategies of agents, where S = d ∈ Ν
𝑆 = 𝑅𝑒𝑐𝑖𝑝𝑟𝑜𝑐𝑖𝑡𝑦, 𝑃𝑟𝑒𝑓𝑒𝑟𝑒𝑛𝑡𝑖𝑎𝑙 𝑎𝑡𝑡𝑎𝑐ℎ𝑚𝑒𝑛𝑡
Connecting with known agents Rich get richer
Not a Web 2.0 Web 2.0Barabasi & Albert, 1999
RQ2
Motivation
Background
and context
Methodology
Conclusions
and Outlook
Technical
Contribution
Test Cases
15. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
15/36
TeLLNet
Monitoring: Mediabase Cube
Mediabase Cube includes all actors of a learning community in
dimensions + additional Time dimension
Results of analysis are stored in Facts tables
RQ2
Klamma, 2010
Motivation
Background
and context
Methodology
Conclusions
and Outlook
Technical
Contribution
Test Cases
16. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
16/36
TeLLNet
Analysis Workflow
interactions of learners Graph-based analysis
Services responsible for mutual engagement dimension
Services responsible for joint enterprises and shared repertoire dimensions
texts of communities Language-based analysis
Social Network
Analysis
Community Detection &
Evolution
Emotional
Analysis
Intent
Analysis
Information
Retrieval
Communities, patterns, emotions, interests, intents
Motivation
Background
and context
Methodology
Conclusions
and Outlook
Technical
Contribution
Test Cases
RQ3
17. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
17/36
TeLLNet
Detection
Define time intervals based on events of communities
𝑖𝑛𝑡𝑒𝑟𝑣𝑎𝑙𝑗 = 𝑏𝑒𝑓𝑜𝑟𝑒𝑗, 𝑎𝑓𝑡𝑒𝑟𝑗 where j is an event
Modularity-based community detection Newman and Girvan, 2004
Propinquity algorithm Zhang et al. 2009
Evolution
Mapping of communities using modified Jaccard index
𝑆𝑖𝑚 𝐶𝑖 𝑗
, 𝐶𝑟 𝑘
= max
𝐶 𝑖 𝑗
⋂𝐶 𝑟 𝑘
𝐶 𝑖 𝑗
,
𝐶 𝑖 𝑗
⋂𝐶 𝑟 𝑘
𝐶 𝑟 𝑘
≥ 𝑡ℎ𝑟𝑒𝑠ℎ𝑜𝑙𝑑
Gliwa et al. 2012
Event extraction Asur et al. 2009
Community events: dissolve, form , merge, split,
and continue
Node events: appear, disappear, join and leave
Community Detection & Evolution
RQ3
Motivation
Background
and context
Methodology
Conclusions
and Outlook
Technical
Contribution
Test Cases
18. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
18/36
TeLLNet
Emotional analysis Pennbaker et al. 2007, Calvo and D‘Mello 2010
Intent analysis Tatu, 2008, Kröll, 2009, Strohmaier et al., 2012
POS tagging + syntactic language patterns
Verb to verb pattern 𝑉𝐵1_𝑡𝑜_𝑉𝐵2, e.g., learn to calculate
Wh-adverb to verb pattern 𝑊𝑅𝐵_𝑡𝑜_𝑉𝐵, e.g., how to estimate
Learning Concepts and Topics Siehndel et al. 2013, d'Aquin and Jay, 2013
Named entities are arguments of information units Grishman and Sundheim, 1996
POS tagging + domain analysis
Linked Open Data Cloud Berners-Lee et al., 2006
Language-based Analysis
Category Examples
posemo awesome, super,
negemo depress…, scary,
anger aggress…, stupid…,
cogmech infer…, problem…,
insight explain…, reason…,
Motivation
Background
and context
Methodology
Conclusions
and Outlook
Technical
Contribution
Test Cases
RQ3
19. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
19/36
TeLLNet
Overview of Case Studies
Modeling Learning Communities in Learning Forums
Competence Management Support for
European Teachers’ Communities
Cultural Analysis of Communities in 13 Wikipedia
language projects
Community
Medium
(Forum)
usesn 1
Community Media
(Project,E-mail, Blog)
uses1 n
TeLLNet
Community
Medium
(Wiki)
usesn 1
originates
from
Country 11
Motivation
Background
and context
Methodology
Conclusions
and Outlook
Technical
Contribution
Test Cases
20. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
20/36
TeLLNet
Modeling Learning Communities
in Learning Forums
The language learning forum URCH
# posts ≈ 429.000 # users ≈ 21.000 # threads ≈
68.000,
Other datasets with 10⁵ - 4,8x10⁵ edges for testing
User patterns (k-means clustering and SNA)
Intent analysis -> learning goals
Emotional analysis -> user attitude
Named entities of community texts
Modeling
Refinement
Monitoring
Analysis
Petrushyna et al., 2014
Petrushyna et al., 2015
A community can be represented by a steeotype model or
models from repository
Stakeholders can decide about changes they need to conduct
in communities
Motivation
Background
and context
Methodology
Conclusions
and Outlook
Technical
Contribution
Test Cases
21. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
21/36
TeLLNet
Modeling Learning Communities
in Learning Forums
The language learning forum URCH
# posts ≈ 429.000 # users ≈ 21.000 # threads ≈
68.000,
Other datasets with 10⁵ - 4,8x10⁵ edges for testing
i* actors: users, threads, forums, user roles, topics of interest
Dependencies: user intents, user activities, actor dependencies
User patterns (k-means clustering and SNA)
Intent analysis -> learning goals
Emotional analysis -> user attitude
Named entities of community texts
Simulations using network strategies: reciprocity and
preferential attachment
A number of possible community states in future
Modeling
Refinement
Monitoring
Analysis
Petrushyna et al., 2014
Petrushyna et al., 2015
Motivation
Background
and context
Methodology
Conclusions
and Outlook
Technical
Contribution
Test Cases
22. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
22/36
TeLLNet
Architecture for
Community Learning Analytics Framework
Motivation
Background
and context
Methodology
Conclusions
and Outlook
Technical
Contribution
Test Cases
23. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
23/36
TeLLNet
How to Realize Continuous Support of Informal
Learning Communities?
01-10.12.2004# posts = 471
# users = 22
# adjacent nodes = 43
# high influence users = 13
# low influence users = 2
need to learn
want to write
take to solve
started to take practice
prepared to take beast
trying to learn stuff
# posts = 226
# users = 20
# adjacent nodes = 15
# high influence users = 4
# low influence users = 4
how to answer
instructed to take writing
supposed to answerplan to take GRE
take to solve
Petrushyna et al., 2015
08-17.12.2004
Models of a learning community in URCH forums
Motivation
Background
and context
Methodology
Conclusions
and Outlook
Technical
Contribution
Test Cases
24. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
24/36
TeLLNet
Strategies:
Reciprocity
only
High
Reciprocity
low PA
50%
Reciprocity
and 50% PA
Can Model Simulations Predict
Community Evolutions?
initial 30 days later
Simulated behaviors of learners differ according to
strategies (reciprocity and preferential attachment (PA))
and activity probabilities (maps)
Betweenness Closeness Clustering Degree
Kolmogorov-Smirnov tests of measure distributions show a better correlation
(<.5) between real and simulated community learners with >39 users
Motivation
Background
and context
Methodology
Conclusions
and Outlook
Technical
Contribution
Test Cases
25. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
25/36
TeLLNet
40% follow life cycle of self-regulated learning in cliques
(tightly connected groups) while others need a support
Estimation of Self-Regulated Theory Using
Community Analysis
Krenge et al., 2011
Nussbaumer et al., 2011
Thread 1
Thread 2
Thread 3
A user of a clique
A non-clique user
in a thread
A clique-user
missing in a
thread
Time
Maintain
Profile
Select
Resource
Learn
Reflect
Motivation
Background
and context
Methodology
Conclusions
and Outlook
Technical
Contribution
Test Cases
26. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
26/36
TeLLNet
21 i* experts evaluated i* models of
learning communities:
social network analysis (71%) and
intent analysis (90%) are helpful for
creating i* models
community stakeholders can
understand community situations
better using i* models (86%)
emphasizing community
requirements for developers (86%)
i* models can be abstract and not
straightforward
Training is required before stakeholders
can use models
Evaluation of Community Analytics Techniques
Social
Network
Analysis
Community
Detection
and
Evolution
Intent
Analysis
Named
Entities
Retrieval
Motivation
Background
and context
Methodology
Conclusions
and Outlook
Technical
Contribution
Test Cases
27. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
27/36
TeLLNet
Competence Management Support for
European Teachers’ Communities
Modeling
Refinement
Monitoring
Analysis
Self-monitoring and self-reflection for teachers Kitsantas, 2002
Other stakeholders refine community situations based on
monitoring and analysis
≈164K teachers, ≈20K projects, ≈39K emails, ≈35K blog posts
Data transformation is required, e. g., ≈ 130K with wrong
country value
Competence indicators for teachers, communities and
stakeholders Song et al., 2011
Analysis of different media networks Pham et al., 2012
i* actors: project performance, activity, popularity, e-mail
communicating skills, etc.
eTwinning let European teachers cooperate with the means of projects, e-mails,
blogs, comments, contact lists, walls, etc.
Competence is the knowledge, skills, attitudes, … related to tasks McClelland, 1973
Motivation
Background
and context
Methodology
Conclusions
and Outlook
Technical
Contribution
Test Cases
28. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
28/36
TeLLNet
How to Support Self-Monitoring of Learners?
Reports for teachers and other stakeholder using competence indicators :
project performance (PP)
e-mail communication (EC)
blog writing (BW)
PP EC BW CW A N
Song et al., 2011
𝐴 𝑡 = 𝑁𝑝𝑟𝑜𝑗 𝑡 +
1
2
× [(𝑁 𝑒𝑚𝑎𝑖𝑙𝑠 𝑜𝑢𝑡 + 𝐶𝑒𝑛𝑡𝑟𝑎𝑙𝑖𝑡𝑦 𝑜𝑢𝑡𝑑𝑒𝑔𝑟𝑒𝑒 + 𝑁 𝑝𝑟𝑜𝑗 𝑏𝑙𝑜𝑔𝑃𝑜𝑠𝑡 𝑡
+
𝑁 𝑏𝑙𝑜𝑔𝐶𝑜𝑚 𝑡 + 𝑁 𝑝𝑟𝑖𝑧𝑒𝐶𝑜𝑚 𝑡 + 𝑁 𝑝𝑟𝑜𝑗𝐶𝑜𝑚 𝑡 ],
where xxx𝐶𝑜𝑚 is a comment in a blog or devoted to a prize or a project
Teacher 1 Teacher 2 Teacher 3 Teacher 4 Teacher 5 Teacher 6
comment writing (CW),
activity(A)
notability (N)
10
8
6
4
2
0
Motivation
Background
and context
Methodology
Conclusions
and Outlook
Technical
Contribution
Test Cases
29. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
29/36
TeLLNet
Estimation of Quality of Project Participation
Using Community Analysis
0 10 20 30 40 50 60 70
0
0.2
0.4
0.6
0.8
1
Frequency
Number of quality labels
(a) Quality labels and number of projects/blogs+blog posts/contacts/wall posts
Blog
Contact
Project
Wall
0 10 20 30 40 50 60 70
0
0.2
0.4
0.6
0.8
1
Degree
Number of quality labels
(b) Quality labels and degree
Blog
Contact
Project
Wall
0 10 20 30 40 50 60 70
0
0.2
0.4
0.6
0.8
1
Betweenness
Number of quality labels
(c) Quality labels and betweenness
Blog
Contact
Project
Wall
0 10 20 30 40 50 60 70
0
0.2
0.4
0.6
0.8
1
Clustering
Number of quality labels
(d) Quality labels and clustering
Blog
Contact
Project
Wall
Quality labels (QL) are prizes according to eTwinning
ambassadors (active stakeholders)
Number of QL correlates positively with betweenness
of teachers in project networks
Pham et al.,2012
Motivation
Background
and context
Methodology
Conclusions
and Outlook
Technical
Contribution
Test Cases
30. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
30/36
TeLLNet
Accelerating Community Detection and
Evolution on Single PC using GPU
Dataset URCH STDocNet
Number of snapshots 378 685
Number of edges ≈300K ≈480K
GPU running time 30 min 22 min
CPU running time > 4 h > 3h
Dataset URCH STDocNet
Number of snapshots 1 1
Number of edges 9110 1188
Number of nodes 857 263
GPU running time 30 min 1.5s
CPU running time ≈2 h 4s
GPU implementation
is efficient for big
networks with > 1K
edges
GPU implementation
allows detection of
huge communities
using just ONE! PC
Motivation
Background
and context
Methodology
Conclusions
and Outlook
Technical
Contribution
Test Cases
GPU
CPU
10K 25K 50K 100K
2.5K
2K
1.5K
1K
0.5K
Seconds
Edges
31. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
31/36
TeLLNet
Contributions and Conclusions
Modeling Refinement Monitoring Analysis
The workflow for Community Learning Analytics:
Toolset for modeling, refinement, monitoring and
analysis of informal online learning communities
Support of informal online learning community
stakeholders by integrating computer science approach
with community of practice theory
A metamodel of learning communities and its
stereotype models
Motivation
Background
and context
Conclusions
and Outlook
Technical
Contribution
Test Cases
Methodology
32. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
32/36
TeLLNet
Contributions in Informal Learning Context
The workflow proposes a structure for analytical
investigation of informal learning communities
A toolset for validating learning theories’ assumptions
Justifying computer science approaches for
community of practice analysis
Abstract modeling of informal learning communities
emphasizing human and non-human agents
Validating existing theoretical community patterns
Motivation
Background
and context
Conclusions
and Outlook
Technical
Contribution
Test Cases
Methodology
33. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
33/36
TeLLNet
Limitations and Follow-up Research
Refinement of the toolset to perform near real-time
monitoring, analysis and modeling Derntl et al., 2015
Extension of community analysis tools with other
techniques, e.g. prediction models of student success
Involvement of new features and strategies for
community simulation
The usage of heterogeneous media: SNSs, Twitter
Motivation
Background
and context
Conclusions
and Outlook
Technical
Contribution
Test Cases
Methodology
34. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
34/36
TeLLNet
Acknowledgements
To my supervisors
To my family
To my colleagues and friends
To my students
TEE
35. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
35/36
TeLLNet
References
Fabian Abel, Ilknur Celik, Claudia Hauff, Laura Hollink, and Geert-Jan Houben. U-Sem: Semantic Enrichment, User Modeling and Mining of Usage Data on the Social Web. In Proceedings of
USEWOD2011 at the 20th WWW Conference, Hyderabad, India, 28 March, 2011.
Sitaram Asur, Srinivasan Parthasarathy, and Duygu Ucar. An Event-based Framework for Characterizing the Evolutionary Behavior of Interaction Graphs. ACM Transactions on Knowledge Discovery
from Data (TKDD), 3(4):16:1–16:36, 2009.
Albert Bandura. Social learning theory. General Learning Press, New York, 1971.
Albert Bandura. Social foundations of thought and action. Englewood Cliffs, NJ Prentice Hall, 1986.
Tim Berners-Lee, Wendy Hall, James Hendler, Nigel Shadbolt, and Daniel J. Weitzner. Creating a Science of the Web. Science 313, no. 5788 (2006): 769‐771. 10.1126/science.1126902.
Albert-László Barabási, Réka Albert: Emergence of scaling in random networks. Science 286(5439), pp. 509–512
Rafael A. Calvo and Sidney D’Mello: Affect Detection: An Interdisciplinary Review of Models, Methods, and Their Applications. Affective Computing, IEEE Transactions on, 1(1), pp. 18–37, 2010.
Cheung, Karen S. K., Lee, Fion S. L., Ip, Rachael K. F. et al. (2005) The Development of Successful On-Line Communities. International Journal of the Computer, the Internet and Management 13(1): 77‐89
McClelland, D. C. Testing for Competence Rather than for "Intelligence”. American Psychologist 20 (1973): 321–333.
Mihai Dascalu, Traian Rebedea, and Stefan Trausan-Matu. A Deep Insight in Chat Analysis: Collaboration, Evolution and Evaluation, Summarization and Search. In Darina Dicheva and Danail Dochev,
editors, Artificial Intelligence: Methodology, Systems, and Applications, volume 6304 of Lecture Notes in Computer Science, pp. 191–200. Springer Berlin Heidelberg, 2010.
Mathieu d’Aquin and Nicolas Jay. Interpreting data mining results with linked data for learning analytics. In Dan Suthers, Katrien Verbert, Erik Duval, and Xavier Ochoa, editors, the Third International
Conference, page 155-164, 2013.
Derntl, Michael, Nicolaescu, Petru, Erdtmann, Stephan, Klamma, Ralf, and Jarke, Matthias. “Near Real-Time Collaborative Conceptual Modeling on the Web.” In Paul Johannesson, Mong Li Lee,
Stephen W. Liddle, Andreas L. Opdahl, Óscar Pastor López Proceedings of the 34th International Conference on Conceptual Modeling (ER 2015), pp.345-356
Pierre Dillenbourg. What do you mean by collaborative learning? In Pierre Dillenbourg, editor, Collaborative-learning: Cognitive and Computational Approaches, pages 1–19. Oxford: Elsevier, 1999b.
Tiago Lopes Ferreira and Alberto Rodrigues Silva: Foster an Implicit Community Based on a Newsletter Tracking System. In Robert Meersman, Herv´e Panetto, Tharam Dillon, Stefanie Rinderle-Ma,
Peter Dadam, Xiaofang Zhou, Siani Pearson, Alois Ferscha, Sonia Bergamaschi, and IsabelF Cruz, editors, On the Move to Meaningful Internet Systems, volume 7565 of Lecture Notes in Computer
Science, pp. 398–415. Springer Berlin Heidelberg, 2012
Danyel Fisher, Marc Smith , Howard T. Welser (2006) You Are Who You Talk To: Detecting Roles in Usenet Newsgroups. In: Proceedings of the 39th Hawaii International Conference on System Sciences,
p 59.2
Bogdan Gliwa, Stanisław Saganowski, Anna Zygmunt, Piotr Brodka, Przemysław Kazienko, and Jarosław Kozlak: Identification of Group Changes in Blogosphere. In Proceedings of International
Conference on Advances in Social Networks Analysis and Mining: Proceedings of ASONAM, pp. 1201–1206. IEEE Computer Society, 2012.
Ralph Grishman and Beth Sundheim. Message Understanding Conference-6: A Brief History. In Proceedings of the 16th Conference on Computational Linguistics: Proceedings of GOLING, volume 1,
pages 466–471, Stroudsburg, PA, USA, 1996. Association for Computational Linguistics.
Andrew Hilts and Eric Yu: Intentional Modeling of Social Media Design Knowledge for Government-Citizen Communication. In Martin Atzmueller, Andreas Hotho, Markus Strohmaier, and Alvin Chin,
editors, Analysis of Social Media and Ubiquitous Data, volume 6904 of Lecture Notes in Computer Science, pp. 20–36. Springer Berlin Heidelberg, 2011.
Matthias Jarke, Ralf Klamma, Gerhard Lakemeyer, and Dominik Schmitz: Continuous, Requirements-Driven Support for Organizations, Networks, and Communities. In Proceedings of the 3rd
International i* Workshop, Recife, Brazil, February 11-12, 2008, pp 47–50
Roula Karam, Piero Fraternali, Alessandro Bozzon, and Luca Galli: Modeling End-Users as Contributors in Human Computation Applications. In Alberto Abell´o, Ladjel Bellatreche, and Boualem
Benatallah, editors, Proceedings of Model and Data Engineering (MEDI) 2012, Poitiers, France , 3-5 October, pp. 3–15. Springer Berlin Heidelberg, 2012.
Ralf Klamma: Werkzeuge und Modelle für die Übergreifende Untersuchung von Social Software. i-com, 9(3), pp. 12–20, 2010.
Ralf Klamma, Zinayida Petrushyna. Pattern-Based Competence Management: On the Gap between Intentions and Reality, In Proceedings of 11th IFIP WG 5.5 Working Conference on Virtual Enterprises
(PRO-VE), St. Etienne, France, October 11-13, 2010, pp. 364-371
Ralf Klamma and Zinayida Petrushyna. The Troll Under the Bridge: Data Management for Huge Web Science Mediabases. In Proceedings of the 38. Jahrestagung der Gesellschaft f¨ur Informatik e.V.
(GI), die INFORMATIK, pages 923–928. Köllen Druck+Verlag GmbH, Bonn, 2008.
Ralf Klamma: Community Learning Analytics – Challenges and Opportunities. In Jhing-Fa Wang and Rynson W. H. Lau, editors, Advances in Web-Based Learning - ICWL 2013: Proceedings of ICWL 2013,
volume 8167 of Lecture Notes in Computer Science, pp. 284–293, Kenting, Taiwan, October 6-9, 2013.
36. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
36/36
TeLLNet
References
Styliani Kleanthous and Vania Dimitrova: Semantic enhanced approach for modelling cognitive relationships in virtual communities. In J. Vassileva, M. Tzagarakis, and V. Dimitrova, editors, Proceedings
of Workshop on Adaptation and Personalisation in Social Systems: Groups, Teams, Communities: Proceedings of Workshop on Adaptation and Personalisation in Social Systems: Groups, Teams,
Communities held at 11th International Conference on UM07, Corfu, Greece, July 25-29, 2007.
Styliani Kleanthous and Vania Dimitrova: Analyzing Community Knowledge Sharing Behavior. In Paul de Bra, Alfred Kobsa, and David Chin, editors, Proceedings of User Modeling, Adaptation, and
Personalization: Proceedings of UMAP, volume 6075 of Lecture Notes in Computer Science, pp. 231–242. Springer Berlin Heidelberg, 2010.
Julian Krenge, Zinayida Petrushyna, Milos Kravcik, Ralf Klamma: Identification of Learning Goals in Forum-based Communities, In Proceedings of 11th IEEE International Conference on Advanced
Learning Technologies (ICALT), Athens, GA, USA, 6-8 July, 2011, pp. 307-309
Kröll, M., and Strohmaier, M. “Analyzing human intentions in natural language text.” Proceedings of the fifth international conference on Knowledge capture (2009): 197–198.
http://portal.acm.org/citation.cfm?id=1597735.1597780.
Madanmohan TR, Navelkar S (2004) Roles and knowledge management in online technology communities: an ethnography study. International Journal of Web Based Communities 1: 71‐89
Mark E. J. Newman and Michelle Girvan: Finding and evaluating community structure in networks. PHYSICAL REVIEW E, 69, 2004.
Helmut M. Niegemann, Steffi Domagk (2005) ELEN project Evaluation Report
Reihaneh Rabbany k., Mansoureh Takaffoli, and Osmar R. Zaiane: Social Network Analysis and Mining to Support the Assessment of On-line Student Participation. SIGKDD Explor. Newsl., 13(2), pp. 20–
29, 2012.
G. Pask and B.C.E. Scott. Learning strategies and individual competence. International Journal of Man-Machine Studies, 4:217–253, 1972.
Seymour Papert. Mindstorms: Children, computers, and powerful ideas. Basic Books, Inc, 1980.
James W. Pennebaker, Cindy K. Chung, Molly. Ireland, Amy. Gonzales, and Roger J. Booth. The Development and Psychometric Properties of LIWC2007, 2007.
Zinayida Petrushyna, Ralf Klamma: No Guru, No Method, No Teacher: Self-Oberservation and Self-Modelling of E-Learning Communities. In Proceedings of 3rd European Conference on Technology
Enhanced Learning, (EC-TEL), Maastricht, The Netherlands, pp. 354-365, September, 2008
Zinayida Petrushyna, Ralf Klamma, Milos Kravcik: Designing During Use: Modeling of Communities of Practice, In Proceedings of 4th IEEE International Conference on Digital Ecosystems and
Technologies (DEST), Dubai, U.A.E., 13-16 April 2010, pp. 612-617
Zinayida Petrushyna, Alexander Ruppert, Ralf Klamma, Dominik Renzel, Matthias Jarke: i*-REST: Light-Weight Modeling with RESTful Web Services. Published in F. Dalpiaz, J. Horkoff, editors,
Proceedings of the Seventh International i* Workshop co-located with the 26th International Conference on Advanced Information Systems Engineering (CAiSE), Thessaloniki, Greece, June 16-17,
2014, CEUR Workshop Proceedings 1157, paper 15.
Jean Piaget. The child’s conception of the world. Paladin, St. Albans, Great Britain, 1973.
Zinayida Petrushyna, Ralf Klamma, Milos Kravcik. On Modeling Learning Communities. In Proceedings of 10th European Conference of Technology Enhanced Learning (EC-TEL), Toledo, Spain,
September 16-18, 2015, pp. 254-267
Manh Cuong Pham, Yiwei Cao, Zinayida Petrushyna, and Ralf Klamma. Learning Analytics in a Teachers’ Social Network. In et al. Hodgson, editor, Proceedings of the Eighth International Conference on
Networked Learning (NLC 2012), 2012.
Maren Scheffel, Katja Niemann, Abelardo Pardo, Derick Leony, Martin Friedrich, Kerstin Schmidt, Martin Wolpers, and Carlos Delgado Kloos: Usage pattern recognitionin student activities. In Carlos
Delgado Kloos, Denis Gilet, Raquel Crespo-Garcia, Fridolin Wild, and Martin Wolpers, editors, Towards Ubiquitous Learning, volume 6964 of Lecture Notes in Computer Science, pp. 341–355. Springer,
2011.
Patrick Siehndel, Ricardo Kawase, Asmelash Teka Hadgu, and Eelco Herder. Finding Relevant Missing References in Learning Courses. In Proceedings of the 22Nd International Conference on World
Wide Web Companion, WWW ’13 Companion, pages 425–430, Republic and Canton of Geneva, Switzerland, 2013. International World Wide Web Conferences Steering Committee.
B.F Skinner. The science of learning and the art of teaching. Harvard Educational Review, pages 88–97, 1954.
Marc A. Smith, Peter Kollock (eds) (1999) Communities in Cyberspace. Routledge, London, New York
Ergang Song, Zinayida Petrushyna, Yiwei Cao, Ralf Klamma: Learning Analytics at Large: The Lifelong Learning Network of 160, 000 European Teachers, In Carlos Delgado Kloos, Denis Gillet, Raquel M.
Crespo García, Fridolin Wild, Martin Wolpers (Eds.): Towards Ubiquitous Learning –Proceedings of 6th European Conference of Technology Enhanced Learning (EC-TEL), Palermo, Italy, September 20-
23, 2011, pp. 398-411
G. Stahl. Group cognition: computer support for building collaborative knowledge. Acting with technology. MIT Press, 2006.
37. Lehrstuhl Informatik 5
(Information Systems)
Prof. Dr. M. Jarke
37/36
TeLLNet
References
Strohmaier, Markus, and Kröll, Mark. “Acquiring knowledge about human goals from Search Query Logs.” Information Processing & Management 48, no. 1 (2012): 63–82.
Hee-Joen Suh and Seung-Wook Lee: Collaborative Learning Agent for Promoting Group Interaction. ETRI, 28(4), pp. 461–474, 2006.
Kimberley Upton and Judy Kay. Narcissus: Group and Individual Models to Support Small Group Work. In Geert-Jan Houben, Gord McCalla, Fabio Pianesi, and Massimo Zancanaro, editors, User
Modeling, Adaptation, and Personalization, volume 5535 of Lecture Notes in Computer Science, pp. 54–65. Springer Berlin Heidelberg, 2009.
Marta Tatu: Discovering Intentions in Text and Semantic Calculus: Intention Overview, Classification, Representation, Discovery and Interactions with Other Semantic Relations. VDM Verlag,
Saarbrücken, Germany, Germany, 2008.
Tammara Combs Turner, Marc A. Smith, Danyel Fisher et al. (2005) Picturing Usenet: Mapping Computer-Mediated Collective Action. Journal of Computer-Mediated Communication 10: 7
Katrien Verbert, Nikos Manouselis, Hendrik Drachsler, and Erik Duval. Dataset-driven research to support learning and knowledge analytics. Educational Technology &Society, 15(3), pp. 133–148, 2012.
Lev Vygotsky. Thought and Language. MIT Press, Cambridge, MA, 1934/1986.
Etienne Wenger: Communities of Practice: Learning, Meaning, and Identity. Cambridge University Press, Cambridge, UK, 1998.
Martin Wolpers, Jad Najjar, Katrien Verbert, and Erik Duval: Tracking Actual Usage:the Attention Metadata Approach. Educational Technology & Society, 10(3), pp. 106– 121, 2007.
Eric Siu-Kwong Yu: Social Modeling and i*. In Conceptual Modeling: Foundations and Applications: Essays in Honor of John Mylopoulos, edited by Alex. Borgida, Akmal B. Chaudhri, Paolo Giorgini and
Eric Siu-Kwong Yu, pp. 99–121. Springer Berlin Heidelberg, 2009.
Yiwen Zhang and Mohan Tanniru: An Agent-Based Approach to Study Virtual Learning Communities. In Proceedings of the 38th Annual Hawaii International Conference on System Sciences, Big Island,
HI, USA, 3-6 January, 2005.
Yuzhou Zhang, Jianyong Wang, Yi Wang, and Lizhu Zhou: Parallel Community Detection on Large Networks with Propinquity Dynamics. In Proceedings of the 15th ACM SIGKDD Conference on
Knowledge and Discovery and Data Mining, Paris, France — June 28 - July 01, 2009, pp. 997–1005.
„Iceberg“ von Created by Uwe Kils (iceberg) and User:Wiska Bodo (sky). - (Work by Uwe Kils) http://www.ecoscope.com/iceberg/. Lizenziert unter CC BY-SA 3.0 über Wikimedia Commons -
https://commons.wikimedia.org/wiki/File:Iceberg.jpg#/media/File:Iceberg.jpg