2012 03 16 (uc3m) emadrid rklamma rwth au analitica aprendizaje mundo movil perspectiva sistemas información comunitaria

1. TeLLNet
Learning Analytics in a Mobile World
A Community Information
Systems Perspective
Ralf Klamma
RWTH Aachen University
Advanced Community Information Systems (ACIS)
klamma@dbis.rwth-aachen.de
This work by Ralf Klamma is licensed under a
Creative Commons Attribution-ShareAlike 3.0 Unported.

2. ACIS @ RWTH TeLLNet
Community Information Systems
Learning Analytics
LA Use Cases
Agenda
Conclusions & Outlook

3. Abstract
With the increasing availability of smart phones and tablets as well as
TeLLNet
growing mobile bandwidth, mobile learning offers by the means of
apps and electronic books become a commodity. In this presentation I
motivate by examples that professional communities need learning
support beyond the commodity level. Learning analytics in such
settings is more than simple assessment strategies but need a deep
understanding of interactions between learners and systems,
learner and learning resources as well as learners among each
others. Such a perspective is delivered by community information
systems serving the needs of mobile communities. The meaningful
combination of quantitative and qualitative assessment strategies
supports the understanding of learner goals, learning processes and
community reflection. Case studies from ongoing EU research projects
like ROLE, GALA and TELMAP will support the argumentation.

4. RWTH Aachen University
• 260 institutes in 9 faculties as Europe’s
TeLLNet leading institutions for science and research
• Currently around 31,400 students are enrolled
in over 100 academic programs
• Over 5,000 of them are international students
hailing from 120 different countries
• 1,250 spin-off businesses have created
around 30,000 jobs in the greater Aachen
region over the past 20 years.
• IDEA League
• Germany’s Excellence Initiative:
3 clusters of excellence, a graduate school
and the institutional strategy “RWTH
Aachen 2020: Meeting Global Challenges”

5. Advanced
Community Information Systems (ACIS)
TeLLNet
Responsive
Web Engineering Open
Community
Web Analytics
Visualization
Community
and
Information
Simulation
Systems
Community Community
Support Analytics
Requirements
Engineering

6. ROLE: Self- and Community
Regulated Learning Processes
TeLLNet
The Horizon Report – 2011 Edition
Based on Fruhmann, Nussbaumer, Albert, 2010

7. Communities of Practice
TeLLNet
 Community of practice (CoP) as the basic concept for
community information systems
 Communities of practice are groups of people who
share a concern or a passion for something they do
and who interact regularly to learn how to do it better
(Wenger, 1998)
 Usability & sociability (Preece, 2000)

8. Learning Analytics Support
 Interdisciplinary multidimensional model of learning networks
TeLLNet
– Social network analysis (SNA) is defining measures for social relations
– i* Framework is defining learning goals and dependencies in
self-regulated learning CoP
– Learning Analytics & Visualization for CoP
social software Media Networks network of artifacts
Wiki, Blog, Podcast, IM, Chat, Microcontent, Blog entry, Message, Burst, Thread,
Email, Newsgroup, Chat … Comment, Conversation, Feedback (Rating)
i*-Dependencies
(Structural, Cross-media)
network of members
Members
(Social Network Analysis: Centrality,
Efficiency)
Communities of practice

9. ROLE Social RE – i* Strategic
Rationale
TeLLNet

10. MobSOS:
Mobile Service Oracle for Success
TeLLNet
 Context-Aware Usage/Error Statistics
 Social Network Analysis
 Service Quality Analysis
 Visualizations
 Set of MobSOS Widgets & Services
 interactive data mining
 visualizations
Dominik Renzel, Ralf Klamma
Semantic Monitoring and Analyzing Context-aware Collaborative Multimedia Services
2009 IEEE International Conference on Semantic Computing, 14-16 September 2009 / Berkeley, CA, USA

11. MediaBase:
Cross Media SNA
 Collection of Social Software
TeLLNet
artifacts with parameterized
PERL scripts
– Blogs & Wikis
– Mails & Forums
– Web pages
 Database support by IBM DB2,
eXist, Oracle, ...
 Web Interface based on Firefox
Plugin, Plone, Drupal, LAS, ...
– www.learningfrontiers.eu
– www.prolearn-academy.org
 Strategies of visualization
– Tree maps
– Cross-media graphs
Klamma et al.: Pattern-Based Cross Media Social Network Analysis for Technology Enhanced Learning in Europe, EC-TEL 2006

12. Case I: Preparation for
English Language Tests
 Urch Forums (formerly TestMagic) User of clique
TeLLNet Non-clique
– Community on preparation for English User in thread
language tests Clique-user
Thread 1 Thread 2 missing in
– 120,000+ threads, 800,000+ posts,
thread
100,000+ users over 10 years
– Social Network Analysis, Machine Thread 3
Learning and Natural Language
Processing
 What are the goals of learners?
– Intent Analysis (Phases 1 & 2) Time
 What are their expressions?
– Sentiment Analysis (Phases 3 & 4)
 Refinement
– 12881 cliques with avg. size 5 and
avg. occurrence of 14
Petrushyna, Kravcik, Klamma:
Learning Analytics for Communities of Lifelong Learners: a Forum Case.
ICALT 2011

13. Self-Regulated Learning Phases
Can Be Observed
Different users
Phase 1 and 2 (low sentiment, questioner, lot of intents)
TeLLNet
Phase 3 (increasing sentiment, conversationalist)
Phase 4 (high sentiment, answering person)
1 week / step
 40% of „footprints“ of cliques align with model for phases

14. Case II: YouTell - A Web 2.0 Service
for Collaborative Storytelling
 Collaborative storytelling  Tagging
TeLLNet  Web 2.0 Service  Ranking/Feedback
 Story search and “pro-  Expert finding
sumption”  Recommending
Klamma, Cao, Jarke: Storytelling on the Web 2.0 as a New Means of Creating Arts
Handbook of Multimedia for Digital Entertainment and Arts, Springer, 2009

15. Knowledge-Dependent
Learning Behaviour in Communities
TeLLNet
 Expert finding algorithm: Knowledge value of community sorted by keywords
 Community behaviors: experts spent more time on the services
 Experts prefers semantic tags while amateurs uses “simple” tags frequently
 Community tags: experts use more precise tags
Renzel, Cao, Lottko, Klamma: Collaborative Video Annotation for Multimedia Sharing between Experts and Amateurs,
WISMA 2010, Barcelona, Spain, May 19-20, 2010

16. Case III: TeLLNet - SNA for European
Teachers‘ Life Long Learning
 How to manage and handle large scale data
TeLLNet on social networks?
 How to analyse social network data in order to
develop teachers’ competence, e.g. to facilitate
a better project collaboration?
 How to make the network visualization useful
for teachers’ lifelong learning?
Song, Petrushyna, Cao, Klamma:
Learning Analytics at Large: The Lifelong Learning Network of 160, 000
European Teachers. EC-TEL 2011

17. Analysis and Visualization of
Lifelong Learner Data
TeLLNet

18. Advanced
Community Information Systems
• LAS & • yFiles SNA
TeLLNet Services • Widgets
• youTell
Responsive • Network
• Advanced Community Models
Open
Web & Visualization
Community • Network
Multimedia & Simulation
Environments Analysis
Technologies
Web Engineering
• Actor Network
Web Analytics
• XMPP Theory
• HTML5 • Communities of
• MPEG-7 Community Community Practice
• Web Support Analytics • Game Theory
Services • Community
• Requirements • MediaBase Detection
• RESTful
Bazaar • MobSOS • Web Mining
• LAS • Recommender
• TellNeT
• Cloud Systems
Computing • Multi Agent
• Mobile Simulation
Computing
Social Requirements Engineering
• Agent and Goal Oriented i* Modeling
• Participatory Community Design

19. Conclusions & Outlook
 Learning Analytics (LA) in lifelong & mobile learner communities is
TeLLNet
based on network and data analysis methods
 LA framework based on modeling & reflection support
– MediaBase: Data Management for LA
– MobSOS: Establishment of LA dashboard and widget collections for
mobile learning communities
 Case studies
– ROLE: Goal and sentiment mining for self-regulated learners
Identification of Learning Phases
– YouTell: Expert vs. amateurs in collaborative storytelling communities
Expert Finding Services
– TellNet: Analysis and visualization of large learner networks
Performance Indicators and Visual Analytics