Upload
ralf-klamma
View
1.783
Download
0
Embed Size (px)
DESCRIPTION
Workshop Knowledge Acquisition on the Social Web 2008, TRIPLE-I Conference, Graz, Austria, September 3-5, 2008
Citation preview
Lehrstuhl Informatik V(Informationssysteme)
Prof. Dr. M. JarkeI5-RK-0808-1
CUELC
Ralf KlammaRWTH Aachen University
KASW Workshop, I-Media, September 3, 2008
Community-Oriented Knowledge Acquisition and Analysis
Lehrstuhl Informatik V(Informationssysteme)
Prof. Dr. M. JarkeI5-RK-0808-2
CUELC
Agenda
Media & Knowledge Communities Case Studies
– Disturbances– Scientific Communities– Community Measures
Conclusions & Outlook Agency & Patienthood in Digital Networks
Agency & Patienthood in Digital Networks
Lehrstuhl Informatik V(Informationssysteme)
Prof. Dr. M. JarkeI5-RK-0808-3
CUELC
Learning & Knowledge ManagementIndividual / Community Perspective
[Nonaka & Takeuchi, 1995]
[Ullman, 2004]
Semantic Knowledgesemiotic concepts
documentation
Verbal
wordslinguistic data
Non-verbal
image, icon, indexvideo blogs, diagrams, images, photographies
Episodic Knowledge memory of experiencing past episodes
web blogs, narratives
Declarative Knowledge Procedural Knowledgesensomotoric skills, procedural scripts
non-documented routines and operations
Lehrstuhl Informatik V(Informationssysteme)
Prof. Dr. M. JarkeI5-RK-0808-4
CUELC
Semiotics in the Tradition of Ferdinand de Saussure (1957 - 1913)
comprehension / articulationactivation of community information system
human neural networkArtifacts of community information system
in p
rese
ntia
in a
bsen
tia
performanceParole
competenceLangue
Lehrstuhl Informatik V(Informationssysteme)
Prof. Dr. M. JarkeI5-RK-0808-5
CUELC
Hypotheses
1. A semiotic knowledge system is dynamic and it changes every time it is activated.
2. The meaning of a concept is determined by how it interacts with other concepts and by how it can be distinguished from other concepts in the knowledge system. (Positive and Negative Knowledge)
3. The knowledge system is carried by a material medium. The modality of the medium influences knowledge structures.
Lehrstuhl Informatik V(Informationssysteme)
Prof. Dr. M. JarkeI5-RK-0808-6
CUELC
Cross-MediaTheory of transcription
Pre-“texts“
TranscriptCross-Media Transcription
Understandand Criticize
Jäger, Stanitzek: Transkribieren - Medien/Lektüre 2002
Strategies of transcriptivity Collection of learning materials are re-structured by new media Design is specific for media and communities by default
Strategies of addressing Social Software promotes the globalization of address spaces Personalization and adaptive strategies are mission critical for CoPs
Strategies of localisation Re-organization of local practices is stimulated by new media like Social Software Need to model practice explicitly
Lehrstuhl Informatik V(Informationssysteme)
Prof. Dr. M. JarkeI5-RK-0808-7
CUELC
Babylonian Talmud: A very old Hypertext
• Scroll/book/printed book • Talmud schools (Jeshiwot) • Authoritative knowledge source• Dialogic encyclopedia • Structure of complex texts• Connected knowledge
Transcribe? Address? Localize?
Lehrstuhl Informatik V(Informationssysteme)
Prof. Dr. M. JarkeI5-RK-0808-8
CUELC
CESE: Multi-lingual Cross-Media System
Published in: DS-NELL 2000, ICALT 2002, ICWL 2002, WWW 2003
Lehrstuhl Informatik V(Informationssysteme)
Prof. Dr. M. JarkeI5-RK-0808-9
CUELC
Research Approach:Reflective Learning Network
Collaborative adaptive learning network
Mining tools for Communities
Measure, Analyse, Simulate
Social Software
Development
Assessment requirements for Communities
Support evolving learning communities (repeated assessment of community requirements)
Based on Preece 2001, cf. I-KNOW 2006 for details
Lehrstuhl Informatik V(Informationssysteme)
Prof. Dr. M. JarkeI5-RK-0808-10
CUELC
Solution idea for Reflective Support:Cross-Media Social Network Analysis
Interdisciplinary multidimensional model of digital networks– Social network analysis (SNA) is defining measures for social
relations– Actor network theory (ANT) is connecting human and media agents– I* framework is defining strategic goals and dependencies– Theory of media transcriptions is studying cross-media knowledge
social softwareWiki, Blog, Podcast, IM, Chat, Email, Newsgroup, Chat …
i*-Dependencies(Structural, Cross-media)
Members(Social Network Analysis: Centrality,
Efficiency)
network of artifactsMicrocontent, Blog entry, Message, Burst, Thread,
Comment, Conversation, Feedback (Rating)
network of members
Communities of practice
Media Networks
Lehrstuhl Informatik V(Informationssysteme)
Prof. Dr. M. JarkeI5-RK-0808-11
CUELC
Simplified Meta Model for ANT using Latour
Actor
Member NetworkLearningService
Medium Artifact
Attribute has
stores creates is affected by belongs go
represents consumes performs ranks
… MatchRetrievalBrowse Search
isA
isA
Latour: On Recalling ANT, 1999Klamma, Spaniol, Cao: A model for social software, IJKL 2007
Lehrstuhl Informatik V(Informationssysteme)
Prof. Dr. M. JarkeI5-RK-0808-12
CUELC
Modeling dependencies using the i* framework
Eric S. K. Yu, Towards Modeling and Reasoning Support for Early-Phase Requirements Engineering, RE 1997
Network
Coordinator
Gatekeeper
Hub
Member
Iterant Broker
URL
isA
isA
isA
isA
Coordination
Artifact
Communication
Legend:
AgentGoalResource Task
Lehrstuhl Informatik V(Informationssysteme)
Prof. Dr. M. JarkeI5-RK-0808-13
CUELC
Disturbances in Cross-media Social Networks
What is a disturbance?– Sensing an incompatibility
between theories exposed and theories-in-use
Disturbances are starting points of learning processes– Disturbances disturb,
prevent … but they are creating reflection
Disturbances are hard to detect or to forecast
Lehrstuhl Informatik V(Informationssysteme)
Prof. Dr. M. JarkeI5-RK-0808-14
CUELC
Pattern Language for PALADIN: Example Troll
Troll Pattern: This pattern tries to discover the cases when a troll exists in a digital social network. A troll in the network is considered a disturbance.
Disturbance: (EXISTS [medium | medium.affordance = threadArtefact]) &
(EXISTS [troll |(EXISTS [thread | (thread.author = troll) & (COUNT [message | (message.author = troll) & (message.posted = thread)]) > minPosts]) & (~EXISTS[ thread1, message1| (thread1.author1 != troll) &
(message1.author = troll & message1.posted = thread1 ]))])])
Forces: medium; troll; network; member; thread; message; url
Force Relations: neighbour(troll, member); own thread(troll, thread)
Solution: No attention must be paid to the discussions started by the troll. Rationale: The troll needs attention to continue its activities. If no attention is paid, he/she
will stop participating in the discussions. Pattern Relations: Associates Spammer pattern.
Lehrstuhl Informatik V(Informationssysteme)
Prof. Dr. M. JarkeI5-RK-0808-15
CUELC
Pattern Discovery ProcessPattern
Disturbance
Variables
Pattern Template
Disturbance
VariablesPattern Parameters
Pattern Template Instance
Pattern Instance
Disturbance
Variables Pattern Parameters
Forces ForceRelations
Rationale
Dependencies
Description Solution
Pattern Relations
Disturbance Instances
Variables Pattern Parameters
Digital Social Network
1. Set pattern parameters
2. Instantiate disturbances
3. Evaluate disturbances
4a. Change Pattern Parameters
4b. Apply Pattern Solution
Lehrstuhl Informatik V(Informationssysteme)
Prof. Dr. M. JarkeI5-RK-0808-16
CUELC
PALADIN Case Study
10 patterns of disturbance over 119 social network instances, 17359 individuals, 215 345 mails
Pattern Occurrences Remarks
Burst 22 The pattern finds out topics which were very important for certain period of time. Scalability is necessary.
No Conversationalist 76 The existence implies little communication in the network.
No Questioner 67 The existence implies that the network is not popular.
No Answering Person
61 Occurs in small networks. The effects of the lack of an answering person must be further checked with content analysis.
Troll 2 Troll occurs very rarely in cultural communities. True negatives exist.
Spammer 86 Spammers can be found often in discussion groups. False positives exist.
Leader 37 The pattern occurs in the network centered around a member.
No Leader 40 Occurs in big networks where the members are distributed in different clusters.
Structural Hole 67 Occurs for members having neighbors with only one contact.
Independent Discussions
13 Occurs in large networks where disconnected subnetworks exist. Scalability is necessary.
Lehrstuhl Informatik V(Informationssysteme)
Prof. Dr. M. JarkeI5-RK-0808-17
CUELC
Impact of research community on individuals
Academic event modeling- Unstructured data of academic events - Diversity of additional media: Photos, Videos, Blogs, Wikis…=> A model for academic events and their communities
documentation
Events recommendation tool for researchers- Design a community based recommendation algorithm
Events communities analysis and visualization.- Community analysis from community of practice point of view
Lehrstuhl Informatik V(Informationssysteme)
Prof. Dr. M. JarkeI5-RK-0808-18
CUELC
AERCS: Evolution of Scientific Communities
Lehrstuhl Informatik V(Informationssysteme)
Prof. Dr. M. JarkeI5-RK-0808-19
CUELC
Evolution of community
VLDB 1990 VLDB 1995
VLDB 2000 VLDB 2006
Lehrstuhl Informatik V(Informationssysteme)
Prof. Dr. M. JarkeI5-RK-0808-20
CUELC
Community visualization – ACM SIGMOD example
ACM SIGMOD
Lehrstuhl Informatik V(Informationssysteme)
Prof. Dr. M. JarkeI5-RK-0808-21
CUELC
Models of Community Success
Reference Model: D&M IS Success Model (1992) – Based on >100 Empirical/Conceptual Studies – Validated by Independent Studies Updated
Model: Integration of Current Concepts – Mobility (Mobile Context) – Multimedia Communities
Lehrstuhl Informatik V(Informationssysteme)
Prof. Dr. M. JarkeI5-RK-0808-22
CUELC
Success Classification & Measurement
Quantitative: Monitoring User-Service – Communication Logging – Mobile Context Information – MobSOS Monitoring Module
Quantitative & Qualitative: Survey – Online User Surveys (Questionnaire) – MobSOS Survey Module
Subjective Objective
Quantitative Monitoring Survey
Qualitative Survey
Lehrstuhl Informatik V(Informationssysteme)
Prof. Dr. M. JarkeI5-RK-0808-23
CUELC
MobSOS Monitoring Module
Client: Capture & Transmit Mobile Context Information
Testbed: Log Communication & Mobile Context
Lehrstuhl Informatik V(Informationssysteme)
Prof. Dr. M. JarkeI5-RK-0808-24
CUELC
Mobile Service Oracle for Success
Monitoring of service invocations Time and position tracking of a service call Recognition of patterns in user behaviour
Lehrstuhl Informatik V(Informationssysteme)
Prof. Dr. M. JarkeI5-RK-0808-25
CUELC
Storytelling Expertfinding
New Measure for Knowledge in a Community
Expert value
Mean: 0,2624# Entries: 99.778
Freq
uenc
y
Lehrstuhl Informatik V(Informationssysteme)
Prof. Dr. M. JarkeI5-RK-0808-26
CUELC
Story-tellling Expert Finding
KeywordsExpert values
Knowledge Value of Community sorted by keywords#
Reco
mm
enda
tions
Expert
Amateur
Lehrstuhl Informatik V(Informationssysteme)
Prof. Dr. M. JarkeI5-RK-0808-27
CUELC
Conclusions Media and Communities shape knowledge structures
– Semiotic systems depend on media– Communities set goals and means
Case Studies– Social Patterns in Communities– Evolution of Scientific Communities– Community Success Models– Expert finding in Communities
Further research– Uncertainty in Tagging systems– Continuous elicitation of community needs– Emotional dimension of collective intelligence