1. CUbRIK Summer School 2014
CUbRIK Summer School 0
histoGraph
Building a social graph for the history
of Europe
Lars Wieneke, CVCE – Luxembourg
2. CUbRIK Summer School 2014
Agenda
The CVCE
What are the Digital Humanities?
The DHLab at the CVCE
Vision: From image collection to Social Graph
The CUbRIK approach
Demo
Challenges, Lessons learned & Outlook
2-4/07/2014 CUbRIK Summer School 1
8. CUbRIK Summer School 2014
WHAT ARE THE DIGITAL
HUMANITIES?
1/10/2011 CUbRIK Presentation 7
9. CUbRIK Summer School 2014
What are the digital humanities?
Digital Humanities is the application of
computational methods and tools for the
humanities
but
„[…] the issue would be not how much
computing we need for getting the answers, but
how much computer science needs us to ask
the right questions.“
http://whatisdigitalhumanities.com, Domenico Fiormonte, Université Roma Tre
1/10/2011 CUbRIK Presentation 8
10. CUbRIK Summer School 2014
What are the digital humanities?
F.Kapplan, EPF Lausanne
Venice Fall Digital Humanities School
2013
1/10/2011 CUbRIK Presentation 9
11. CUbRIK Summer School 2014
What are the digital humanities?
F.Kapplan, EPF Lausanne
Venice Fall Digital Humanities School
2013
1/10/2011 CUbRIK Presentation 10
12. CUbRIK Summer School 2014
The DHLab at the CVCE
European Integration
Studies
Humanities
DHLab
Development
&
Operations
1/10/2011 CUbRIK Presentation 11
13. CUbRIK Summer School 2014
OUR VISION: BUILDING A
SOCIAL GRAPH FROM IMAGE
COLLECTIONS
1/10/2011 CUbRIK Presentation 12
14. Building a social graph from image
collections
CUbRIK Summer School 2014
1/10/2011 CUbRIK Presentation 13
13
15. Building a social graph from image
collections
CUbRIK Summer School 2014
1/10/2011 CUbRIK Presentation 14
17. CUbRIK Summer School 2014
Four pillars
Researcher Requirements
Entity Repository
Efficient Indexation Process
Toolchain for visualization and analysis
1/10/2011 CUbRIK Presentation 16
18. CUbRIK Summer School 2014
Sourcing researcher requirements
Requirements
User pull
Technology
push
1/10/2011 CUbRIK Presentation 17
19. CUbRIK Summer School 2014
Sourcing researcher requirements
Selection of target
user group
First draft of the app
scenario
Feedback on
technical scope
Exploratory
interviews
(daily work practices)
Second draft of the
app scenario
Focus group
(user needs and app
scenarios)
Feedback on
technical feasability
Lessons learned:
issues and features
Specification
Implementation 1.
demonstrator
Stage 1
Stage 2
Stage 3
1/10/2011 CUbRIK Presentation 18
Stage 4
Users Requirements Technology
20. Feedback on
technical feasability
Stage 2
CUbRIK Summer School 2014
app scenario
Focus group
Sourcing (user needs and researcher app
requirements
scenarios)
Lessons learned:
issues and features
Specification Implementation 1.
demonstrator
Workshop: Review of
app and features
Revised specification Implementation 2.
demonstrator
Evaluation and test
Stage 3
Stage 4
Stage 5
Users Requirements Technology
1/10/2011 CUbRIK Presentation 19
21. CUbRIK Summer School 2014
Building an entity repository
1/10/2011 CUbRIK Presentation 20
22. CUbRIK Summer School 2014
Efficient indexation
Conflict
(e.g., “Image contains
‘Romano Prodi’ ”
? Confidence = low)
Conflict store Conflict
manager
Conflict resolution
task store
Conflict resolution
task: conflict,
required skill, priority, ..
CUbRIK app
for Conflict
resolution
Game Crowdtask Q&A
1/10/2011 CUbRIK Presentation 21
23. CUbRIK Summer School 2014
Efficient indexation
Face
detect ion
Face
ident ifi cat ion
Clickworkers
Crowd Face
posit ion
validat ion
Expert
validat ion
Expert
Crowd
Collect ion
ingest ion
Social Graph
creat ion
SMILA
1/10/2011 CUbRIK Presentation 22
25. CUbRIK Summer School 2014
Challenges
Detection and identification of
identities/places/events in time
Verification of identities/places/events in time
Analysis of relationships (e.g. co-occurrences)
Rights aware crawling and storage
Verification of provenance and license
information
Truth and provenance
1/10/2011 CUbRIK Presentation 24
26. CUbRIK Summer School 2014
Approach
Crowd-sourced verification of detected faces
(false positives/negatives)
Verification of identities through/places/events in
time social networks of experts
Visual knowledge discovery/exploration
Integrated rights aware crawling and storage
Integrated license and provenance management
1/10/2011 CUbRIK Presentation 25
27. CUbRIK Summer School 2014
Discursive interface
Voting (ref. Stackoverflow) is supported
through source referencing and
Problem
space
Shared
visualization
explanations. Solution
space
Multiple
perspectives
1/10/2011 CUbRIK Presentation 26
28. CUbRIK Summer School 2014
Motivation, gamification and
reputation
Different levels of motivation for different tasks
Face position validation -> Monetary incentives
Face validation -> reputation gain
Actions in the application can be rewarded
through the system and through other users
Goal to motivate AND to capture reputation
1/10/2011 CUbRIK Presentation 27
29. CUbRIK Summer School 2014
Lessons learned
No one truth in history but interpretation,
context and discussion
Therefore need to represent ambivalence,
contradictions and discussion
Close ties between data representation (Social
graph) and their original context (primary
sources)
1/10/2011 CUbRIK Presentation 28
30. CUbRIK Summer School 2014
Next step: evaluation
4 week evaluation phase in July
kick-off with a physical workshop in Luxembourg
Closure with a virtual workshop
1/10/2011 CUbRIK Presentation 29
31. CUbRIK Summer School 2014
THANK YOU FOR YOUR
ATTENTION
1/10/2011 CUbRIK Presentation 30