Humanist machine interaction with histoGraph
0 likes760 views
The Cubrik project focuses on human-machine interaction in the digital humanities, particularly in mapping the social graph of European integration. It aims to enhance multimedia searches by integrating human expertise to verify identities and relationships in historical data, utilizing crowdsourcing for verification tasks. The project seeks to address challenges related to data representation, copyright, and the integration of diverse data sources while fostering collaboration among researchers.
Humanist machine interaction with histoGraph
- 1. CUbRIK Presentation 0 Humanist-Machine Interaction for the digital humanities Building the Social graph of the History of European Integration DHLU 2013 www.cubrikproject.eu
- 2. About CUbRIK European Community's Seventh FrameworkProgram FP7-ICT 15 European partners Multimedia searchprocessing: Puttinghumans in the loop Demos: History of Europeand Fashion CUbRIK Presentation 1
- 3. CUbRIK Presentation 2 Why CUbRIK approach Human in the loop added value: Verification of identities/places/events ambiguous and temporal onlypossible by putting humans in the loop Integration of multiple perspectives CUbRIK as an open toolbox allows follow-up and extension through third parties “ Vertical”integration: GUI, components, crowdsourcing integrated in a platform
- 4. Specification process: User pull & technology push CUbRIK Presentation 3
- 5. The situation today More and more sources such as images, textsand videos are being digitalized How can we extract high-level information fromthem? Harnessing the effectiveness of machines andthe expertise of (expert) crowds For starters: 3000 images representing thehistory of European integration, more documentsto come soon CUbRIK Presentation 4
- 6. 5 History of Europe App Name: HoE App Domain: digital humanities Target users: researchers in digital humanities Rationale: software-enhanced social hermeneuticsbased on heterogeneous multimedia archives Researcher approach Researchers manually verify information about historical photos Neglects aggregate information from different sources that could lead to new insights CUbRIK solution: Full pipeline for the discovery of relationships in heterogeneous data Integration of human and machine computation Visualization of relationships Discursive interface enabling the mapping of multiple perspectives CUbRIK Presentation
- 7. 6 Main Challenges The main challenges in the HoE app: 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 Approach: Crowd-sourced verification of detected faces (false positives/negatives) Verification of identities through/places/events in timesocial networks ofexperts Visual knowledge discovery/exploration Integrated rights aware crawling and storage Integrated license and provenance management CUbRIK Presentation
- 8. CUbRIKin a nutshell CUbRIK Presentation 7
- 9. Pipelining the CUbRIKcomponents: Conflict resolution CUbRIK Presentation 8 Raw content High level features (automatic annotations) 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
- 10. Pipelining the CUbRIKcomponents: Human input from click-workers Great choice for simple tasks: Face detection: false positives, false negatives Monetary motivation, via www.microtask.com Poor performance on complex tasks: Low resolution images Different angles etc. Actors recurring over time CUbRIK Presentation 9
- 11. Pipelining the CUbRIKcomponents: Human input from experts Capable of complex tasks: In-depth knowledge of key actors Context knowledge allows inferences But: Different motivational models! Public goods Reputation CUbRIK Presentation 10
- 12. Pipelining the CUbRIKcomponents: Towards a community of experts Time for a Demo! CUbRIK Presentation 11
- 13. Usage for historians No one truth in history but interpretation, context and discussion Therefore need to represent ambivalence, contradictions and discussion Close ties between data representation (Socialgraph) and their original context (primarysources) CUbRIK Presentation 12
- 14. Conclusion& Outlook Challenges Whatistruth? Humanitiesvs. Computer Science Gatheringrequirementsfortoolsthathaven‘tbeendevelopedyet Engagingcrowds Image copyrights Refinementoftheapplication Additional datasources Improvementoftheinterface Integration ofthedifferent components CUbRIK Presentation 13
- 15. WWW.CUBRIKPROJECT.EU Visituson CUbRIK Presentation 14 @CUBRIKPROJECT Or follow us on Twitter