SlideShare a Scribd company logo
1 of 30
Trusting user-contributed data in
Cultural Heritage Domain
Archana Nottamkandath
(Work done with Davide Ceolin & Wan Fokkink)
VU University Amsterdam
COMMIT/SEALINC
1
Context
• COMMIT/SEALINC project
• Museums have collections which can be
annotated with user-contributed information
COMMIT/SEALINC 2
Can we directly trust the user provided
content?
COMMIT/SEALINC 3
Can we trust the user provided
content directly? – Apparently Not!
COMMIT/SEALINC 4
Solution: Manually evaluate
annotations
COMMIT/SEALINC 5
Accept
Not sure
Reject
But…
100,000+ Paintings and Annotations!
Evaluation costs Resources
• Is expensive manual labor
• Costs a lot of time
• Requires adherence to museum policies
– Museum X [Accept, not sure, reject]
– Museum Y [Foreign, Judgmental, Strong reject,
Strong accept ]..
COMMIT/SEALINC 7
Need for automated trust analysis
• Algorithms automatically/ semi-automatically
evaluate annotations
COMMIT/SEALINC 8
(a) Flower
(b) 19th
century
(c) Sunshine
(d) Vermeer
(e) Bronze
Automated Trust analysis algorithms
• Requirements
– High accuracy (Accurately predict evaluations
most of the time)
– Minimum input from cultural heritage
professionals
– Scalable and Efficient (w.r.t resources and time)
– Works with different cultural heritage data
COMMIT/SEALINC 9
Definition
• Trustworthy annotation
– Relevant to image
– Enhances/re-instates existing knowledge
– Is acceptable by museums policies to be published
on their website
COMMIT/SEALINC 10
Used
Accurator Interface
Existing workflow
COMMIT/SEALINC 11
Tulips
Roses
Night Sky
Van Gogh
Buddhist
Portrait
Monument
Asian
War
memorial
User_name: Jones
contributed
Tags
Integrate Trust to Existing workflow
(Research Question1)
COMMIT/SEALINC 12
Tulips
Roses
Night Sky
Van Gogh
Buddhist
Portrait
Monument
Asian
War
memorial
User_name: Jones
contributed
Used
Accurator Interface
Tags
RQ1:How to determine trust from user contributing
annotations to the system?
Integrate Trust to Existing workflow
(Research Question 2)
COMMIT/SEALINC 13
Tulips
Roses
Night Sky
Van Gogh
Buddhist
Portrait
Monument
Asian
War
memorial
User_name: Jones
contributed
Used
Accurator Interface
Tags
RQ2: How to determine trust from the Annotation Process?
Integrate Trust to Existing workflow
(Research Question 3)
COMMIT/SEALINC 14
Tulips
Roses
Night Sky
Van Gogh
Buddhist
Portrait
Monument
Asian
War
memorial
User_name: Jones
contributed
Used
Accurator Interface
Tags
RQ3: How to determine trust from contributed data?
RQ1:Determine trust from users[1]
• Evaluate subset of user tags
COMMIT/SEALINC 15
Tulips
Roses
Night Sky
Van Gogh
Buddhist
Portrait
Monument
Asian
War
memorial
User_name: Jones Test set
Roses
Night sky
Van Gogh
Asian
War
Memorial
contributed
Train set
Tulips
Van Gogh
Buddhist
Monument
Evaluates
Museum
• User expert on one topic might be expert on
similar topics
COMMIT/SEALINC 16
Expert on
Tulips
Possibly
Expert on
Possibly
Expert on
Roses
Lilies
User_name: Jones
Test set
Roses
Night sky
Van Gogh
Asian
War
Memorial
Train
setTulips
Van Gogh
Buddhist
Monument
RQ1:Determine trust from users[1]
With a certain probability
RQ1:Determine trust from users[2]
• User profile : [Experience, education, country,
gender, income, museum visits…]
COMMIT/SEALINC 17
Steve.museum
dataset
RQ1:Determine trust from users[2]
• Predict user reputation using Support Vector
Machines(SVM)
• [Feature1, Feature2, ..] -> Category of user
– [21 yrs, Female, Bachelors, Australia] -> Excellent
– [60 yrs, Male, PhD, America] -> Good
– [56 yrs, Female, Masters, Croatia] -> Bad
– [30 yrs, Male, High School, Mexico] -> ?
COMMIT/SEALINC 18
RQ2: Determine trust from Annotation
process
• Time of day, Day of week, Day of month etc.
affect user quality
• Typing speed affects user quality
– Typing fast might indicate higher confidence
COMMIT/SEALINC 19
Tulips
Van Gogh
Buddhist
Monument
Rich Lady
Plant
Leonardo
Bronze plate
RQ2: Determine trust from Annotation
process
• Predict tag quality using Support Vector
Machines(SVM)
• [Feature1, Feature2, ....] -> Category of Tag
– [10:00, Monday, June, 3s] -> Excellent
– [12:00, Wednesday, 15s] -> Good
– [23:56, Friday, April, 80s] -> Bad
– [06:00, Thursday, March, 70s] -> ?
COMMIT/SEALINC 20
RQ2: Determine trust from Annotation
process
• Why is this important?
– Useful for anonymous users who did not fill profile
information
COMMIT/SEALINC 21
RQ3: Determine trust from data
• Contributed data itself has features, train SVM
on features to predict quality of tag
– Length
– Specificity
– Presence in vocabularies
– Times already contributed
– Noun
COMMIT/SEALINC 22
Tulips
Van Gogh
Buddhist
Monument
[6,specific, yes, English, 10, no…] -> Good
[7,specific, yes, Dutch, 1,yes…] -> Bad
Goals achieved
• Requirements
– High accuracy (Accurately predict evaluations
most of the time)
– Minimum input from cultural heritage
professionals
– Scalable and efficient
– Works with different cultural heritage data
COMMIT/SEALINC 23
Goal 1: High Accuracy
COMMIT/SEALINC 24
– High accuracy (Accurately predict evaluations
most of the time)
• Predicted quality of a tag based on user profile with
accuracy from 68% to 72%
COMMIT/SEALINC 25
Steve dataset results
Goal 1: High Accuracy
Goal 2: Minimum input from
Cultural Heritage Institutions
• Algorithms require minimum of 5 evaluated
tags per user for predictions
• Working on to minimize/eliminate this
requirement
COMMIT/SEALINC 26
Goal 3: Scalable and efficient
• Reduced computation time while maintaining
accuracy in Steve dataset
COMMIT/SEALINC 27
Goal 4: Works with different
cultural heritage data
• Steve Museum dataset
• Waisda? Dataset
– Video Tagging Game
• SEALINC Media experiments at CWI
COMMIT/SEALINC 28
Future Work
• Employ our experiences and algorithms to
analyze the data from Accurator
• Employ trust scores for ranking in search
• Identify techniques to visualize trust
COMMIT/SEALINC 29
Thank you
a.nottamkandath@vu.nl
COMMIT/SEALINC 30

More Related Content

Viewers also liked

Moving from downloads to uploads: Toward an understanding of the curricular i...
Moving from downloads to uploads: Toward an understanding of the curricular i...Moving from downloads to uploads: Toward an understanding of the curricular i...
Moving from downloads to uploads: Toward an understanding of the curricular i...
Darren Milligan
 

Viewers also liked (16)

Academic Programs & Search Optimization
Academic Programs & Search OptimizationAcademic Programs & Search Optimization
Academic Programs & Search Optimization
 
ICOM Moscow 2014 with audio - The Virtual Museum
ICOM Moscow 2014 with audio - The Virtual MuseumICOM Moscow 2014 with audio - The Virtual Museum
ICOM Moscow 2014 with audio - The Virtual Museum
 
Crowdsourcing as productive engagement with cultural heritage
Crowdsourcing as productive engagement with cultural heritageCrowdsourcing as productive engagement with cultural heritage
Crowdsourcing as productive engagement with cultural heritage
 
It Strategy Session Cio Roundtable May 27 2010
It Strategy Session   Cio Roundtable May 27 2010It Strategy Session   Cio Roundtable May 27 2010
It Strategy Session Cio Roundtable May 27 2010
 
Cloud Application Marketplace Overview
Cloud Application Marketplace OverviewCloud Application Marketplace Overview
Cloud Application Marketplace Overview
 
Viral content strategy for universities and schools
Viral content strategy for universities and schoolsViral content strategy for universities and schools
Viral content strategy for universities and schools
 
Digital Kids and Technology Bias - Girl Geeks TO Edition
Digital Kids and Technology Bias - Girl Geeks TO EditionDigital Kids and Technology Bias - Girl Geeks TO Edition
Digital Kids and Technology Bias - Girl Geeks TO Edition
 
A TRANSVERSE DIGITAL STRATEGY AT THE JEWISH MUSEUM BERLIN by Mirjam Wenzel (D...
A TRANSVERSE DIGITAL STRATEGY AT THE JEWISH MUSEUM BERLIN by Mirjam Wenzel (D...A TRANSVERSE DIGITAL STRATEGY AT THE JEWISH MUSEUM BERLIN by Mirjam Wenzel (D...
A TRANSVERSE DIGITAL STRATEGY AT THE JEWISH MUSEUM BERLIN by Mirjam Wenzel (D...
 
Unit economics example for B2B SaaS company
Unit economics example for B2B SaaS companyUnit economics example for B2B SaaS company
Unit economics example for B2B SaaS company
 
Museums content strategy_workshop_ConxaRoda
Museums content strategy_workshop_ConxaRodaMuseums content strategy_workshop_ConxaRoda
Museums content strategy_workshop_ConxaRoda
 
Take Better Care of Library Data and Spreadsheets with Google Visualization A...
Take Better Care of Library Data and Spreadsheets with Google Visualization A...Take Better Care of Library Data and Spreadsheets with Google Visualization A...
Take Better Care of Library Data and Spreadsheets with Google Visualization A...
 
Moving from downloads to uploads: Toward an understanding of the curricular i...
Moving from downloads to uploads: Toward an understanding of the curricular i...Moving from downloads to uploads: Toward an understanding of the curricular i...
Moving from downloads to uploads: Toward an understanding of the curricular i...
 
Jack the Museum (Museums in the Age of Scale) -- Text version
Jack the Museum (Museums in the Age of Scale) -- Text versionJack the Museum (Museums in the Age of Scale) -- Text version
Jack the Museum (Museums in the Age of Scale) -- Text version
 
Design for What Matters With Content Strategy
Design for What Matters With Content StrategyDesign for What Matters With Content Strategy
Design for What Matters With Content Strategy
 
Competitive Research to Fuel Conversion - Michael Stricker - Conversion Confe...
Competitive Research to Fuel Conversion - Michael Stricker - Conversion Confe...Competitive Research to Fuel Conversion - Michael Stricker - Conversion Confe...
Competitive Research to Fuel Conversion - Michael Stricker - Conversion Confe...
 
Information architecture 101
Information architecture 101Information architecture 101
Information architecture 101
 

Similar to Rijksmuseum presentation

Visitor Evaluations Communications Report
Visitor Evaluations Communications ReportVisitor Evaluations Communications Report
Visitor Evaluations Communications Report
Allison Kopplin
 
Franziska Frey 2 / DHV13
Franziska Frey 2 / DHV13Franziska Frey 2 / DHV13
Franziska Frey 2 / DHV13
Frederic Kaplan
 
Gallery One, One Year Later - Jane Alexander, Chief Information Officer and S...
Gallery One, One Year Later - Jane Alexander, Chief Information Officer and S...Gallery One, One Year Later - Jane Alexander, Chief Information Officer and S...
Gallery One, One Year Later - Jane Alexander, Chief Information Officer and S...
MCN (Museum Computer Network)
 
MW2014 - Gallery One, The First Year: Sustainability, Evaluation Process,
MW2014  - Gallery One, The First Year: Sustainability, Evaluation Process, MW2014  - Gallery One, The First Year: Sustainability, Evaluation Process,
MW2014 - Gallery One, The First Year: Sustainability, Evaluation Process,
Jane Alexander
 
Use of the Smartphone at Dallas Museum of Art - by Gail Davitt
Use of the Smartphone at Dallas Museum of Art - by Gail DavittUse of the Smartphone at Dallas Museum of Art - by Gail Davitt
Use of the Smartphone at Dallas Museum of Art - by Gail Davitt
Museums & Galleries NSW
 

Similar to Rijksmuseum presentation (20)

Exploring Evaluation Methods for Digital Technologies – Elizabeth Bolander, D...
Exploring Evaluation Methods for Digital Technologies – Elizabeth Bolander, D...Exploring Evaluation Methods for Digital Technologies – Elizabeth Bolander, D...
Exploring Evaluation Methods for Digital Technologies – Elizabeth Bolander, D...
 
Visitor Evaluations Communications Report
Visitor Evaluations Communications ReportVisitor Evaluations Communications Report
Visitor Evaluations Communications Report
 
Lampeter sliseshare
Lampeter sliseshareLampeter sliseshare
Lampeter sliseshare
 
Bringing sites to life with iBeacons
Bringing sites to life with iBeaconsBringing sites to life with iBeacons
Bringing sites to life with iBeacons
 
Franziska Frey 2 / DHV13
Franziska Frey 2 / DHV13Franziska Frey 2 / DHV13
Franziska Frey 2 / DHV13
 
Exhibitly Public Presentation
Exhibitly Public PresentationExhibitly Public Presentation
Exhibitly Public Presentation
 
Gallery One, One Year Later - Jane Alexander, Chief Information Officer and S...
Gallery One, One Year Later - Jane Alexander, Chief Information Officer and S...Gallery One, One Year Later - Jane Alexander, Chief Information Officer and S...
Gallery One, One Year Later - Jane Alexander, Chief Information Officer and S...
 
MW2014 - Gallery One, The First Year: Sustainability, Evaluation Process,
MW2014  - Gallery One, The First Year: Sustainability, Evaluation Process, MW2014  - Gallery One, The First Year: Sustainability, Evaluation Process,
MW2014 - Gallery One, The First Year: Sustainability, Evaluation Process,
 
8 Jane Alexander, Chief Information Officer for Cleveland Museum of Art
8 Jane Alexander, Chief Information Officer for Cleveland Museum of Art8 Jane Alexander, Chief Information Officer for Cleveland Museum of Art
8 Jane Alexander, Chief Information Officer for Cleveland Museum of Art
 
Case Study: The building of ArtsConnectEd through strategic digital asset cre...
Case Study: The building of ArtsConnectEd through strategic digital asset cre...Case Study: The building of ArtsConnectEd through strategic digital asset cre...
Case Study: The building of ArtsConnectEd through strategic digital asset cre...
 
Digital Art History
Digital Art HistoryDigital Art History
Digital Art History
 
Showcasing Student Scholarship
Showcasing Student Scholarship Showcasing Student Scholarship
Showcasing Student Scholarship
 
Evaluating visitor experience in foyers
Evaluating visitor experience in foyersEvaluating visitor experience in foyers
Evaluating visitor experience in foyers
 
Use of the Smartphone at Dallas Museum of Art - by Gail Davitt
Use of the Smartphone at Dallas Museum of Art - by Gail DavittUse of the Smartphone at Dallas Museum of Art - by Gail Davitt
Use of the Smartphone at Dallas Museum of Art - by Gail Davitt
 
Leicester Castle tells its story: ibeacon-based mobile interpretation
Leicester Castle tells its story: ibeacon-based mobile interpretationLeicester Castle tells its story: ibeacon-based mobile interpretation
Leicester Castle tells its story: ibeacon-based mobile interpretation
 
International Image Interoperability Framework panel at #CIDOC2017 conference
International Image Interoperability Framework panel at #CIDOC2017 conferenceInternational Image Interoperability Framework panel at #CIDOC2017 conference
International Image Interoperability Framework panel at #CIDOC2017 conference
 
History navigator
History navigatorHistory navigator
History navigator
 
[系列活動] 人工智慧與機器學習在推薦系統上的應用
[系列活動] 人工智慧與機器學習在推薦系統上的應用[系列活動] 人工智慧與機器學習在推薦系統上的應用
[系列活動] 人工智慧與機器學習在推薦系統上的應用
 
Public-Art-201-compressed.pdf
Public-Art-201-compressed.pdfPublic-Art-201-compressed.pdf
Public-Art-201-compressed.pdf
 
Digitization of the Tuol Sleng Genocide Museum Archives
Digitization of the Tuol Sleng Genocide Museum ArchivesDigitization of the Tuol Sleng Genocide Museum Archives
Digitization of the Tuol Sleng Genocide Museum Archives
 

Recently uploaded

Spellings Wk 4 and Wk 5 for Grade 4 at CAPS
Spellings Wk 4 and Wk 5 for Grade 4 at CAPSSpellings Wk 4 and Wk 5 for Grade 4 at CAPS
Spellings Wk 4 and Wk 5 for Grade 4 at CAPS
AnaAcapella
 
會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文
會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文
會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文
中 央社
 
Personalisation of Education by AI and Big Data - Lourdes Guàrdia
Personalisation of Education by AI and Big Data - Lourdes GuàrdiaPersonalisation of Education by AI and Big Data - Lourdes Guàrdia
Personalisation of Education by AI and Big Data - Lourdes Guàrdia
EADTU
 
SPLICE Working Group: Reusable Code Examples
SPLICE Working Group:Reusable Code ExamplesSPLICE Working Group:Reusable Code Examples
SPLICE Working Group: Reusable Code Examples
Peter Brusilovsky
 

Recently uploaded (20)

The Story of Village Palampur Class 9 Free Study Material PDF
The Story of Village Palampur Class 9 Free Study Material PDFThe Story of Village Palampur Class 9 Free Study Material PDF
The Story of Village Palampur Class 9 Free Study Material PDF
 
Spring gala 2024 photo slideshow - Celebrating School-Community Partnerships
Spring gala 2024 photo slideshow - Celebrating School-Community PartnershipsSpring gala 2024 photo slideshow - Celebrating School-Community Partnerships
Spring gala 2024 photo slideshow - Celebrating School-Community Partnerships
 
Spellings Wk 4 and Wk 5 for Grade 4 at CAPS
Spellings Wk 4 and Wk 5 for Grade 4 at CAPSSpellings Wk 4 and Wk 5 for Grade 4 at CAPS
Spellings Wk 4 and Wk 5 for Grade 4 at CAPS
 
Including Mental Health Support in Project Delivery, 14 May.pdf
Including Mental Health Support in Project Delivery, 14 May.pdfIncluding Mental Health Support in Project Delivery, 14 May.pdf
Including Mental Health Support in Project Delivery, 14 May.pdf
 
OS-operating systems- ch05 (CPU Scheduling) ...
OS-operating systems- ch05 (CPU Scheduling) ...OS-operating systems- ch05 (CPU Scheduling) ...
OS-operating systems- ch05 (CPU Scheduling) ...
 
Observing-Correct-Grammar-in-Making-Definitions.pptx
Observing-Correct-Grammar-in-Making-Definitions.pptxObserving-Correct-Grammar-in-Making-Definitions.pptx
Observing-Correct-Grammar-in-Making-Definitions.pptx
 
Sternal Fractures & Dislocations - EMGuidewire Radiology Reading Room
Sternal Fractures & Dislocations - EMGuidewire Radiology Reading RoomSternal Fractures & Dislocations - EMGuidewire Radiology Reading Room
Sternal Fractures & Dislocations - EMGuidewire Radiology Reading Room
 
ĐỀ THAM KHẢO KÌ THI TUYỂN SINH VÀO LỚP 10 MÔN TIẾNG ANH FORM 50 CÂU TRẮC NGHI...
ĐỀ THAM KHẢO KÌ THI TUYỂN SINH VÀO LỚP 10 MÔN TIẾNG ANH FORM 50 CÂU TRẮC NGHI...ĐỀ THAM KHẢO KÌ THI TUYỂN SINH VÀO LỚP 10 MÔN TIẾNG ANH FORM 50 CÂU TRẮC NGHI...
ĐỀ THAM KHẢO KÌ THI TUYỂN SINH VÀO LỚP 10 MÔN TIẾNG ANH FORM 50 CÂU TRẮC NGHI...
 
會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文
會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文
會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文
 
Stl Algorithms in C++ jjjjjjjjjjjjjjjjjj
Stl Algorithms in C++ jjjjjjjjjjjjjjjjjjStl Algorithms in C++ jjjjjjjjjjjjjjjjjj
Stl Algorithms in C++ jjjjjjjjjjjjjjjjjj
 
FICTIONAL SALESMAN/SALESMAN SNSW 2024.pdf
FICTIONAL SALESMAN/SALESMAN SNSW 2024.pdfFICTIONAL SALESMAN/SALESMAN SNSW 2024.pdf
FICTIONAL SALESMAN/SALESMAN SNSW 2024.pdf
 
PSYPACT- Practicing Over State Lines May 2024.pptx
PSYPACT- Practicing Over State Lines May 2024.pptxPSYPACT- Practicing Over State Lines May 2024.pptx
PSYPACT- Practicing Over State Lines May 2024.pptx
 
Personalisation of Education by AI and Big Data - Lourdes Guàrdia
Personalisation of Education by AI and Big Data - Lourdes GuàrdiaPersonalisation of Education by AI and Big Data - Lourdes Guàrdia
Personalisation of Education by AI and Big Data - Lourdes Guàrdia
 
Andreas Schleicher presents at the launch of What does child empowerment mean...
Andreas Schleicher presents at the launch of What does child empowerment mean...Andreas Schleicher presents at the launch of What does child empowerment mean...
Andreas Schleicher presents at the launch of What does child empowerment mean...
 
Trauma-Informed Leadership - Five Practical Principles
Trauma-Informed Leadership - Five Practical PrinciplesTrauma-Informed Leadership - Five Practical Principles
Trauma-Informed Leadership - Five Practical Principles
 
Improved Approval Flow in Odoo 17 Studio App
Improved Approval Flow in Odoo 17 Studio AppImproved Approval Flow in Odoo 17 Studio App
Improved Approval Flow in Odoo 17 Studio App
 
ESSENTIAL of (CS/IT/IS) class 07 (Networks)
ESSENTIAL of (CS/IT/IS) class 07 (Networks)ESSENTIAL of (CS/IT/IS) class 07 (Networks)
ESSENTIAL of (CS/IT/IS) class 07 (Networks)
 
24 ĐỀ THAM KHẢO KÌ THI TUYỂN SINH VÀO LỚP 10 MÔN TIẾNG ANH SỞ GIÁO DỤC HẢI DƯ...
24 ĐỀ THAM KHẢO KÌ THI TUYỂN SINH VÀO LỚP 10 MÔN TIẾNG ANH SỞ GIÁO DỤC HẢI DƯ...24 ĐỀ THAM KHẢO KÌ THI TUYỂN SINH VÀO LỚP 10 MÔN TIẾNG ANH SỞ GIÁO DỤC HẢI DƯ...
24 ĐỀ THAM KHẢO KÌ THI TUYỂN SINH VÀO LỚP 10 MÔN TIẾNG ANH SỞ GIÁO DỤC HẢI DƯ...
 
Book Review of Run For Your Life Powerpoint
Book Review of Run For Your Life PowerpointBook Review of Run For Your Life Powerpoint
Book Review of Run For Your Life Powerpoint
 
SPLICE Working Group: Reusable Code Examples
SPLICE Working Group:Reusable Code ExamplesSPLICE Working Group:Reusable Code Examples
SPLICE Working Group: Reusable Code Examples
 

Rijksmuseum presentation

  • 1. Trusting user-contributed data in Cultural Heritage Domain Archana Nottamkandath (Work done with Davide Ceolin & Wan Fokkink) VU University Amsterdam COMMIT/SEALINC 1
  • 2. Context • COMMIT/SEALINC project • Museums have collections which can be annotated with user-contributed information COMMIT/SEALINC 2
  • 3. Can we directly trust the user provided content? COMMIT/SEALINC 3
  • 4. Can we trust the user provided content directly? – Apparently Not! COMMIT/SEALINC 4
  • 7. Evaluation costs Resources • Is expensive manual labor • Costs a lot of time • Requires adherence to museum policies – Museum X [Accept, not sure, reject] – Museum Y [Foreign, Judgmental, Strong reject, Strong accept ].. COMMIT/SEALINC 7
  • 8. Need for automated trust analysis • Algorithms automatically/ semi-automatically evaluate annotations COMMIT/SEALINC 8 (a) Flower (b) 19th century (c) Sunshine (d) Vermeer (e) Bronze
  • 9. Automated Trust analysis algorithms • Requirements – High accuracy (Accurately predict evaluations most of the time) – Minimum input from cultural heritage professionals – Scalable and Efficient (w.r.t resources and time) – Works with different cultural heritage data COMMIT/SEALINC 9
  • 10. Definition • Trustworthy annotation – Relevant to image – Enhances/re-instates existing knowledge – Is acceptable by museums policies to be published on their website COMMIT/SEALINC 10
  • 11. Used Accurator Interface Existing workflow COMMIT/SEALINC 11 Tulips Roses Night Sky Van Gogh Buddhist Portrait Monument Asian War memorial User_name: Jones contributed Tags
  • 12. Integrate Trust to Existing workflow (Research Question1) COMMIT/SEALINC 12 Tulips Roses Night Sky Van Gogh Buddhist Portrait Monument Asian War memorial User_name: Jones contributed Used Accurator Interface Tags RQ1:How to determine trust from user contributing annotations to the system?
  • 13. Integrate Trust to Existing workflow (Research Question 2) COMMIT/SEALINC 13 Tulips Roses Night Sky Van Gogh Buddhist Portrait Monument Asian War memorial User_name: Jones contributed Used Accurator Interface Tags RQ2: How to determine trust from the Annotation Process?
  • 14. Integrate Trust to Existing workflow (Research Question 3) COMMIT/SEALINC 14 Tulips Roses Night Sky Van Gogh Buddhist Portrait Monument Asian War memorial User_name: Jones contributed Used Accurator Interface Tags RQ3: How to determine trust from contributed data?
  • 15. RQ1:Determine trust from users[1] • Evaluate subset of user tags COMMIT/SEALINC 15 Tulips Roses Night Sky Van Gogh Buddhist Portrait Monument Asian War memorial User_name: Jones Test set Roses Night sky Van Gogh Asian War Memorial contributed Train set Tulips Van Gogh Buddhist Monument Evaluates Museum
  • 16. • User expert on one topic might be expert on similar topics COMMIT/SEALINC 16 Expert on Tulips Possibly Expert on Possibly Expert on Roses Lilies User_name: Jones Test set Roses Night sky Van Gogh Asian War Memorial Train setTulips Van Gogh Buddhist Monument RQ1:Determine trust from users[1] With a certain probability
  • 17. RQ1:Determine trust from users[2] • User profile : [Experience, education, country, gender, income, museum visits…] COMMIT/SEALINC 17 Steve.museum dataset
  • 18. RQ1:Determine trust from users[2] • Predict user reputation using Support Vector Machines(SVM) • [Feature1, Feature2, ..] -> Category of user – [21 yrs, Female, Bachelors, Australia] -> Excellent – [60 yrs, Male, PhD, America] -> Good – [56 yrs, Female, Masters, Croatia] -> Bad – [30 yrs, Male, High School, Mexico] -> ? COMMIT/SEALINC 18
  • 19. RQ2: Determine trust from Annotation process • Time of day, Day of week, Day of month etc. affect user quality • Typing speed affects user quality – Typing fast might indicate higher confidence COMMIT/SEALINC 19 Tulips Van Gogh Buddhist Monument Rich Lady Plant Leonardo Bronze plate
  • 20. RQ2: Determine trust from Annotation process • Predict tag quality using Support Vector Machines(SVM) • [Feature1, Feature2, ....] -> Category of Tag – [10:00, Monday, June, 3s] -> Excellent – [12:00, Wednesday, 15s] -> Good – [23:56, Friday, April, 80s] -> Bad – [06:00, Thursday, March, 70s] -> ? COMMIT/SEALINC 20
  • 21. RQ2: Determine trust from Annotation process • Why is this important? – Useful for anonymous users who did not fill profile information COMMIT/SEALINC 21
  • 22. RQ3: Determine trust from data • Contributed data itself has features, train SVM on features to predict quality of tag – Length – Specificity – Presence in vocabularies – Times already contributed – Noun COMMIT/SEALINC 22 Tulips Van Gogh Buddhist Monument [6,specific, yes, English, 10, no…] -> Good [7,specific, yes, Dutch, 1,yes…] -> Bad
  • 23. Goals achieved • Requirements – High accuracy (Accurately predict evaluations most of the time) – Minimum input from cultural heritage professionals – Scalable and efficient – Works with different cultural heritage data COMMIT/SEALINC 23
  • 24. Goal 1: High Accuracy COMMIT/SEALINC 24
  • 25. – High accuracy (Accurately predict evaluations most of the time) • Predicted quality of a tag based on user profile with accuracy from 68% to 72% COMMIT/SEALINC 25 Steve dataset results Goal 1: High Accuracy
  • 26. Goal 2: Minimum input from Cultural Heritage Institutions • Algorithms require minimum of 5 evaluated tags per user for predictions • Working on to minimize/eliminate this requirement COMMIT/SEALINC 26
  • 27. Goal 3: Scalable and efficient • Reduced computation time while maintaining accuracy in Steve dataset COMMIT/SEALINC 27
  • 28. Goal 4: Works with different cultural heritage data • Steve Museum dataset • Waisda? Dataset – Video Tagging Game • SEALINC Media experiments at CWI COMMIT/SEALINC 28
  • 29. Future Work • Employ our experiences and algorithms to analyze the data from Accurator • Employ trust scores for ranking in search • Identify techniques to visualize trust COMMIT/SEALINC 29

Editor's Notes

  1. Digital museums have 100’s of 1000’s of prints online