histograph: a case study in digital humanities

Post on 19-Jun-2015

206 Views

Category:

Technology

2 Downloads

Preview:

Click to see full reader

DESCRIPTION

The CUbRIK histograph application illustrated at the EMPOLIS Executive Forum 2014, Berlin, by Lars Wieneke (CVCE)

TRANSCRIPT

History of Europe A case study in digital humanities

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

www.cvce.eu

09/04/2014 – History of Europe. A case study in digital humanities Dr.-Ing. Lars Wieneke, Head of Information & Technology, CVCE Luxembourg

www.cvce.eu  

5

www.cvce.eu

09/04/2014 – History of Europe. A case study in digital humanities Dr.-Ing. Lars Wieneke, Head of Information & Technology, CVCE Luxembourg

www.cvce.eu  

6

www.cvce.eu

09/04/2014 – History of Europe. A case study in digital humanities Dr.-Ing. Lars Wieneke, Head of Information & Technology, CVCE Luxembourg

www.cvce.eu  

7

What are the digital humanities?

„[…] 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

8

What are the Digital Humanities?

Digital Humanities is the application of computational methods and tools for the humanities   but

9

What are the Digital Humanities? Challenges

F.Kapplan, EPF Lausanne Venice  Fall  Digital  Humani3es  School  2013  

10

What are the Digital Humanities? Challenges

F.Kapplan, EPF Lausanne Venice  Fall  Digital  Humani3es  School  2013  

11

The DHLab at the CVCE

European  Integra3on  Studies  Humani'es  

Development  &    

Opera3ons  

DHLab  

12

Our vision: Building a social graph from image collections

13

Building a social graph from image collections

Building a social graph from image collections

15

The CUbRIK Approach

The CUbRIK approach

•  European Community's Seventh Framework Program FP7-ICT

•  15 European partners •  Multimedia search

processing: Putting humans in the loop

•  Combination of human and machine computation

16 Lars Wieneke, CVCE, Luxembourg

The CUbRIK approach: four pillars

17 Lars Wieneke, CVCE, Luxembourg

Researcher  Requirements  

En3ty  Repository  

Efficient  Indexa3on  Process  

Toolchain  for  visualiza3on  and  analysis  

Requirements  

User  pull  

Technology  push  

Sourcing researcher requirements

18 Lars Wieneke, CVCE, Luxembourg 18 Lars Wieneke, CVCE, Luxembourg

Sourcing researcher requirements

19 Lars Wieneke, CVCE, Luxembourg 19 Lars Wieneke, CVCE, Luxembourg

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

Workshop: Review of app and features

Revised specification

Implementation 2. demonstrator

Evaluation and test

Stage 1

Stage 2

Stage 3

Stage 4

Stage 5

Users Requirements Technology

Users Requirements Technology

Building an Entity Repository

20 Lars Wieneke, CVCE, Luxembourg 20 Lars Wieneke, CVCE, Luxembourg

Efficient indexation

21 Lars Wieneke, CVCE, Luxembourg 21 Lars Wieneke, CVCE, Luxembourg

Raw content 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 Q&A Crowdtask

Efficient indexation

22 Lars Wieneke, CVCE, Luxembourg 22 Lars Wieneke, CVCE, Luxembourg

Face detection

Face identification

Clickworkers

Crowd Face position

validation

Expert Crowd

Expert validation

Collection ingestion

Social Graph creation

SMILA  

Demo

23 Lars Wieneke, CVCE, Luxembourg 23 Lars Wieneke, CVCE, Luxembourg

Challenges

24 Lars Wieneke, CVCE, Luxembourg 24 Lars Wieneke, CVCE, Luxembourg

•  Main 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

•  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

Lessons learned

25 Lars Wieneke, CVCE, Luxembourg 25 Lars Wieneke, CVCE, Luxembourg

•  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)

Outlook

26 Lars Wieneke, CVCE, Luxembourg 26 Lars Wieneke, CVCE, Luxembourg

•  Integration of other document types

•  Improvement of the interface

•  Pre-filtering of identities

•  Gamification and social reputation for expert annotation

27

Thank you for listening

29/09/2011 – Title

28 29/09/2011 – Titre

top related