SlideShare a Scribd company logo
1 of 35
Download to read offline
What is the problem?                How can we deal with concept drift?   Open questions




             Studying Concept Drift in Political Ontologies

                        Shenghui Wang1,2 Stefan Schlobach1
                        Janet Takens2 Wouter van Atteveldt2

                             1
                               Department of Computer Science
                         2
                             Department of Communication Science
                                Vrije Universiteit Amsterdam



                       Workshop on Matching and Meaning 2010
What is the problem?                    How can we deal with concept drift?   Open questions



Content analysis in Communication Science



              Communication scientists study all sorts of media content
              related to human communication
              Content analysis based on the NET method
                       concepts: political actors and issues
                       relations: associations, opinions, or actions.

      Example
      Het Openbaar Ministerie (OM) wil de komende vier jaar mensen-
      handel uitroeien.
What is the problem?                    How can we deal with concept drift?   Open questions



Content analysis in Communication Science



              Communication scientists study all sorts of media content
              related to human communication
              Content analysis based on the NET method
                       concepts: political actors and issues
                       relations: associations, opinions, or actions.

      Example
      Het Openbaar Ministerie (OM) wil de komende vier jaar mensen-
      handel uitroeien.
What is the problem?                    How can we deal with concept drift?   Open questions



Content analysis in Communication Science

              Communication scientists study all sorts of media content
              related to human communication
              Content analysis based on the NET method
                       concepts: political actors and issues
                       relations: associations, opinions, or actions.

      Example
      Het Openbaar Ministerie (OM) wil de komende vier jaar mensen-
      handel uitroeien.



                                      -1
                           om                         human trafficking
What is the problem?                                                 How can we deal with concept drift?                                                                                   Open questions



Semantic network analysis

                                                                    2271                     1067                   1388                  740                   1373
                                              2127
                         2467                                                                                                                                                      1268




                                                                                  2351
                                                                                                         907
                                                            1223                                                                                  1739
                                       1708                                                                                   2516
                                                                                                                                                                      1706
                        2393
                                                                                               2438                                                                                 1721
                                                                            1077
                                                                                                                    1052
                                                 2323                                                                                           1234
                                                               1034                                   2394
                                                                                                                                                                      964
                                 1275                                              2120                                           1936
                       1059                                                                                    1045
                                                                                                2221                                               2124                             2753
                                                     2171            2653
                                                                                       752
                                                                                                                       2655          2054                              856
                                       693                                                            1608
                                                                           341                                                                     2647
                                                            1011
                        2806                                                            1145                   1625
                                                                                                                            2076                                                     648
                                                 1386                                               1233
                                                                       1545                                                               329
                                                                                                                                                          480                361
                                 475                                                    845                         1906
                                                             2259
                                                                                                       883                    1439
                       2090                                                1474                                                                 1332
                                               2002                                                                                                               2377
                                                                                         1306                   2077
                                                                                                                                                                                     548
                                                            654
                                2696                                                                   2606                              2492
                                                                       1635                                            2471                              484
                                                                                         956
                                                                                                                                                                            889
                                               2199

                                                              1198                               623            2614
                       2573                                                      545                                              1409            1259
                                                                                                                                                                                    2251

                                 1940
                                                                                                                                                                      2751
                                                      539                                                1827
                                                                      870                2186                              2151                 2423




                         464
                                                                                                                                                                                   1097
                                        1841                 2070                                            1073                                              1932
                                                                                   438                                              2403
What is the problem?                    How can we deal with concept drift?   Open questions



Network-based communication science study




              Politicians are networking
              Politics is perceived by citizens via media
              Media study by semantic network analysis
                       Who   is determining the subjects?
                       Who   is teaming up?
                       Who   is more credible?
                       Who   owns which topic?
What is the problem?                   How can we deal with concept drift?      Open questions



Before network analysis




      We first need to extract networks!
              How do we extract such networks?
                       Requires: large corpora with annotated textual content
                            Manual coding against coding books (ontologies)
                            Automated content analysis in progress
What is the problem?                   How can we deal with concept drift?      Open questions



Before network analysis




      We first need to extract networks!
              How do we extract such networks?
                       Requires: large corpora with annotated textual content
                            Manual coding against coding books (ontologies)
                            Automated content analysis in progress
What is the problem?                   How can we deal with concept drift?        Open questions



What is the problem?




      Problems with constructing annotated content
              Data from different time periods or genres
              Coded by different teams at different moments
                       Manifesto Research Group: 25 countries, from 1945 to 2006
                       Comparative Policy Agendas project: media content,
                       manifestos, legislative texts, government press statements, etc.
                       Election campaign coverage from 1994 to 2006
What is the problem?                   How can we deal with concept drift?        Open questions



What is the problem?




      Problems with constructing annotated content
              Data from different time periods or genres
              Coded by different teams at different moments
                       Manifesto Research Group: 25 countries, from 1945 to 2006
                       Comparative Policy Agendas project: media content,
                       manifestos, legislative texts, government press statements, etc.
                       Election campaign coverage from 1994 to 2006
What is the problem?                How can we deal with concept drift?   Open questions



What is the problem?




      Problem 1: Interoperability problem while information sharing
          Different coding books should be merged or at least
          connected
                       illegal immigration
                       labour migrants
What is the problem?           How can we deal with concept drift?   Open questions



What is the problem, again?




      Everything changes, quickly or slowly ...
What is the problem?   How can we deal with concept drift?   Open questions



Follow the Fashion?
What is the problem?             How can we deal with concept drift?   Open questions



Women’s role?




              Suffragettes said that women’s role in society is unacceptable
              Pope says that women’s role in society is unacceptable
What is the problem?               How can we deal with concept drift?   Open questions



Concept drift is a problem




      Problem 2: Concept drift
              Meaning of concepts changes over time
              Analysis based on evolving concepts must consider temporal
              locality
              Study concept drift itself is useful
What is the problem?             How can we deal with concept drift?   Open questions



Datasets




              Five political ontologies which were used to annotate
              newspaper articles
              23639 manually annotated newspaper articles during five
              recent Dutch national election campaigns
              There even exist manual mappings but most of them are
              lexically very similar
What is the problem?             How can we deal with concept drift?   Open questions



What are the main issues?




              What is concept drift?
              How do we detect the concept drift?
              How do we represent the concept drift?
              How do we evaluate the concept drift?
              How do we use the concept drift?
What is the problem?             How can we deal with concept drift?   Open questions



What are the main issues?




              What is concept drift?
              How do we detect the concept drift?
              How do we represent the concept drift?
              How do we evaluate the concept drift?
              How do we use the concept drift?
What is the problem?             How can we deal with concept drift?   Open questions



What are the main issues?




              What is concept drift?
              How do we detect the concept drift?
              How do we represent the concept drift?
              How do we evaluate the concept drift?
              How do we use the concept drift?
What is the problem?             How can we deal with concept drift?   Open questions



What are the main issues?




              What is concept drift?
              How do we detect the concept drift?
              How do we represent the concept drift?
              How do we evaluate the concept drift?
              How do we use the concept drift?
What is the problem?             How can we deal with concept drift?   Open questions



What are the main issues?




              What is concept drift?
              How do we detect the concept drift?
              How do we represent the concept drift?
              How do we evaluate the concept drift?
              How do we use the concept drift?
What is the problem?             How can we deal with concept drift?    Open questions



What is concept drift?


      Definition
      The meaning of concept
              Label
              Intension
              Extension
      Questions:
              Can three of them change at the same time?
              Should there be a rigid part in one concept which stays
              constant all the time?
What is the problem?             How can we deal with concept drift?    Open questions



What is concept drift?


      Definition
      The meaning of concept
              Label
              Intension
              Extension
      Questions:
              Can three of them change at the same time?
              Should there be a rigid part in one concept which stays
              constant all the time?
What is the problem?             How can we deal with concept drift?    Open questions



What is concept drift?


      Definition
      The meaning of concept
              Label
              Intension
              Extension
      Questions:
              Can three of them change at the same time?
              Should there be a rigid part in one concept which stays
              constant all the time?
What is the problem?             How can we deal with concept drift?    Open questions



What is concept drift?


      Definition
      The meaning of concept
              Label
              Intension
              Extension
      Questions:
              Can three of them change at the same time?
              Should there be a rigid part in one concept which stays
              constant all the time?
What is the problem?              How can we deal with concept drift?     Open questions



Detecting concept drift




      Detecting concept drift in terms of
              its labels
              its extension: instance-based mapping between different time
              its intension: using its hierarchical information and the
              co-occurrence links to other concepts of the same time
What is the problem?   How can we deal with concept drift?   Open questions



Representing concept drift
What is the problem?                                       How can we deal with concept drift?                                                           Open questions



Representing concept drift: Builder’ fraud

                                                                           criminaliteit




             fiod       companies,_coroprations,_business                   criminaliteit


                          0.077        0.002


                                  bouwfraude           fraude_en_corruptie

                                          2006

                                                                               0.030          0.044


                                                                                0.038                 bestuurlijke_vernieuwing


                                                                                                                                             0.047


                                                      0.043                                        parlementaire_enquete_algemeen




                                                                0.154        corruptie                  parlementaire_enquete_bouwfrau


                                                                                                       0.198


                                                                bouwfraude                 0.034                       0.097

                                                                                                        2003

                                                                   0.050                      0.130                 0.117                  0.152 0.124


                                                           klokkenluider                   belangenverstrengeling              jusititie


                                                                        0.083                                  0.058


                                                                    bouwfraude

                                                                                               2002
What is the problem?                                                                 How can we deal with concept drift?                                                                                             Open questions



Representing concept drift: Police


                                 criminaliteit




                               criminaliteit


                                                                0.065        0.067


           0.030   criminaliteitsbestrijding         0.072


                               0.046             0.055


                            politie                          criminaliteit           justitie



                      2006

                                                                    0.151         0.107            0.069


                                                                        politie           0.037   criminaliteit       jusititie



                                                                         2003

                                                                                          0.055         0.073     0.052                0.042


                                                                                                     politie                  0.044   rcriminaliteit        xjustitie



                                                                                                               2002

                                                                                                                                             0.066      0.071                         0.064


                                                                                                                                         rpolitie                       sjo_creawetsto                criminelen   0.066   0.120



                                                                                                                                                     1998

                                                                                                                                                                               0.083          0.123


                                                                                                                                                                            politie



                                                                                                                                                                                         1994
What is the problem?   How can we deal with concept drift?   Open questions



What kinds of concept drift can we detect?
What is the problem?                             How can we deal with concept drift?                                Open questions



What kinds of concept drift can we detect?


      Association shifting

                                                                  hervorming_politiebestel             hgekozen_burgemeester


                                                                              0.018                 0.033


                soc_vernieuwing          ontwikkelingshu          hbestuurlijke_vernieuwin

                                                                                             1998

                                         0.082   0.074


                                         best_vernieuwin

                                  1994
What is the problem?                       How can we deal with concept drift?           Open questions



What kind of concept drift can we detect?
      Generalising or specialising



                                                       criminality




                                         0.038          fraud and corruption




                            corruption                builder’s fraud            0.043

                                                                  2006



                       builder’s fraud

                           2003
What is the problem?                      How can we deal with concept drift?            Open questions



What kind of concept drift can we detect?

      Overlapping


                                                 rwerkgevers                lkoppeling


                                                0.013               0.015


                       wgv_werkgevers           rvno               0.037        0.077

                                                                 1998

                                  0.077


                              vno_ncw

                           1994
What is the problem?             How can we deal with concept drift?   Open questions



Open questions




              What other types of concept drift can we identify and
              automatically detect?
              What is an appropriate (formal) representation for the
              detected drift?
              How can we evaluate the detected concept drift, both
              qualitatively and quantitatively?
What is the problem?   How can we deal with concept drift?   Open questions




      Thank you

More Related Content

Viewers also liked

Голосовые технологии
Голосовые технологииГолосовые технологии
Голосовые технологииSystemGroup
 
I n s u r a n c e / J o b
I n s u r a n c e    /   J o bI n s u r a n c e    /   J o b
I n s u r a n c e / J o bLIC
 
3C Delhi 1 , delhi one Noida 9910008816
3C Delhi 1 , delhi one Noida 99100088163C Delhi 1 , delhi one Noida 9910008816
3C Delhi 1 , delhi one Noida 9910008816Sandeep arora
 
3C sports Village Noida
3C sports Village Noida3C sports Village Noida
3C sports Village NoidaSandeep arora
 
delhi one commercial noida 9910008816
delhi one commercial noida 9910008816delhi one commercial noida 9910008816
delhi one commercial noida 9910008816Sandeep arora
 
Aims sector-15Land mark towers @ 9990585032
Aims sector-15Land mark towers @ 9990585032 Aims sector-15Land mark towers @ 9990585032
Aims sector-15Land mark towers @ 9990585032 Sandeep arora
 
Government 2.1 - Let The Virtual Journey Begins, NOW: From Desktop To the Clo...
Government 2.1 - Let The Virtual Journey Begins, NOW: From Desktop To the Clo...Government 2.1 - Let The Virtual Journey Begins, NOW: From Desktop To the Clo...
Government 2.1 - Let The Virtual Journey Begins, NOW: From Desktop To the Clo...HKITF
 
Moodle essay quiz question
Moodle essay quiz questionMoodle essay quiz question
Moodle essay quiz questionPilgrim Library
 
Решение для мобильной торговли
Решение для мобильной торговлиРешение для мобильной торговли
Решение для мобильной торговлиSystemGroup
 
How having my website hacked opened up career opportunities
How having my website hacked opened up career opportunitiesHow having my website hacked opened up career opportunities
How having my website hacked opened up career opportunitiesValentin Vesa
 

Viewers also liked (13)

Голосовые технологии
Голосовые технологииГолосовые технологии
Голосовые технологии
 
I n s u r a n c e / J o b
I n s u r a n c e    /   J o bI n s u r a n c e    /   J o b
I n s u r a n c e / J o b
 
3C Delhi 1 , delhi one Noida 9910008816
3C Delhi 1 , delhi one Noida 99100088163C Delhi 1 , delhi one Noida 9910008816
3C Delhi 1 , delhi one Noida 9910008816
 
Desenhos
DesenhosDesenhos
Desenhos
 
Searching 101
Searching 101Searching 101
Searching 101
 
Ssp ebook internet_mktg
Ssp ebook internet_mktgSsp ebook internet_mktg
Ssp ebook internet_mktg
 
3C sports Village Noida
3C sports Village Noida3C sports Village Noida
3C sports Village Noida
 
delhi one commercial noida 9910008816
delhi one commercial noida 9910008816delhi one commercial noida 9910008816
delhi one commercial noida 9910008816
 
Aims sector-15Land mark towers @ 9990585032
Aims sector-15Land mark towers @ 9990585032 Aims sector-15Land mark towers @ 9990585032
Aims sector-15Land mark towers @ 9990585032
 
Government 2.1 - Let The Virtual Journey Begins, NOW: From Desktop To the Clo...
Government 2.1 - Let The Virtual Journey Begins, NOW: From Desktop To the Clo...Government 2.1 - Let The Virtual Journey Begins, NOW: From Desktop To the Clo...
Government 2.1 - Let The Virtual Journey Begins, NOW: From Desktop To the Clo...
 
Moodle essay quiz question
Moodle essay quiz questionMoodle essay quiz question
Moodle essay quiz question
 
Решение для мобильной торговли
Решение для мобильной торговлиРешение для мобильной торговли
Решение для мобильной торговли
 
How having my website hacked opened up career opportunities
How having my website hacked opened up career opportunitiesHow having my website hacked opened up career opportunities
How having my website hacked opened up career opportunities
 

More from Shenghui Wang

Non-parametric Subject Prediction
Non-parametric Subject PredictionNon-parametric Subject Prediction
Non-parametric Subject PredictionShenghui Wang
 
Our journey with semantic embedding
Our journey with semantic embeddingOur journey with semantic embedding
Our journey with semantic embeddingShenghui Wang
 
Linking entities via semantic indexing
Linking entities via semantic indexingLinking entities via semantic indexing
Linking entities via semantic indexingShenghui Wang
 
Semantic indexing for KOS
Semantic indexing for KOSSemantic indexing for KOS
Semantic indexing for KOSShenghui Wang
 
Contextualization of topics - browsing through terms, authors, journals and c...
Contextualization of topics - browsing through terms, authors, journals and c...Contextualization of topics - browsing through terms, authors, journals and c...
Contextualization of topics - browsing through terms, authors, journals and c...Shenghui Wang
 
Exploring a world of networked information built from free-text metadata
Exploring a world of networked information built from free-text metadataExploring a world of networked information built from free-text metadata
Exploring a world of networked information built from free-text metadataShenghui Wang
 
Ariadne's Thread -- Exploring a world of networked information built from fre...
Ariadne's Thread -- Exploring a world of networked information built from fre...Ariadne's Thread -- Exploring a world of networked information built from fre...
Ariadne's Thread -- Exploring a world of networked information built from fre...Shenghui Wang
 
Learning Concept Mappings from Instance Similarity
Learning Concept Mappings from Instance SimilarityLearning Concept Mappings from Instance Similarity
Learning Concept Mappings from Instance SimilarityShenghui Wang
 
Measuring the dynamic bi-directional influence between content and social ne...
Measuring the dynamic bi-directional influence between content and social ne...Measuring the dynamic bi-directional influence between content and social ne...
Measuring the dynamic bi-directional influence between content and social ne...Shenghui Wang
 
Similarity Features, and their Role in Concept Alignment Learning
Similarity Features, and their Role in Concept Alignment Learning Similarity Features, and their Role in Concept Alignment Learning
Similarity Features, and their Role in Concept Alignment Learning Shenghui Wang
 
What is concept dirft and how to measure it?
What is concept dirft and how to measure it?What is concept dirft and how to measure it?
What is concept dirft and how to measure it?Shenghui Wang
 

More from Shenghui Wang (12)

Non-parametric Subject Prediction
Non-parametric Subject PredictionNon-parametric Subject Prediction
Non-parametric Subject Prediction
 
Our journey with semantic embedding
Our journey with semantic embeddingOur journey with semantic embedding
Our journey with semantic embedding
 
Linking entities via semantic indexing
Linking entities via semantic indexingLinking entities via semantic indexing
Linking entities via semantic indexing
 
Semantic indexing for KOS
Semantic indexing for KOSSemantic indexing for KOS
Semantic indexing for KOS
 
Contextualization of topics - browsing through terms, authors, journals and c...
Contextualization of topics - browsing through terms, authors, journals and c...Contextualization of topics - browsing through terms, authors, journals and c...
Contextualization of topics - browsing through terms, authors, journals and c...
 
Exploring a world of networked information built from free-text metadata
Exploring a world of networked information built from free-text metadataExploring a world of networked information built from free-text metadata
Exploring a world of networked information built from free-text metadata
 
Ariadne's Thread -- Exploring a world of networked information built from fre...
Ariadne's Thread -- Exploring a world of networked information built from fre...Ariadne's Thread -- Exploring a world of networked information built from fre...
Ariadne's Thread -- Exploring a world of networked information built from fre...
 
Learning Concept Mappings from Instance Similarity
Learning Concept Mappings from Instance SimilarityLearning Concept Mappings from Instance Similarity
Learning Concept Mappings from Instance Similarity
 
Measuring the dynamic bi-directional influence between content and social ne...
Measuring the dynamic bi-directional influence between content and social ne...Measuring the dynamic bi-directional influence between content and social ne...
Measuring the dynamic bi-directional influence between content and social ne...
 
Similarity Features, and their Role in Concept Alignment Learning
Similarity Features, and their Role in Concept Alignment Learning Similarity Features, and their Role in Concept Alignment Learning
Similarity Features, and their Role in Concept Alignment Learning
 
What is concept dirft and how to measure it?
What is concept dirft and how to measure it?What is concept dirft and how to measure it?
What is concept dirft and how to measure it?
 
ECCS 2010
ECCS 2010ECCS 2010
ECCS 2010
 

Recently uploaded

CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):comworks
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 3652toLead Limited
 
Artificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning eraArtificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning eraDeakin University
 
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024BookNet Canada
 
Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024Neo4j
 
APIForce Zurich 5 April Automation LPDG
APIForce Zurich 5 April  Automation LPDGAPIForce Zurich 5 April  Automation LPDG
APIForce Zurich 5 April Automation LPDGMarianaLemus7
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubKalema Edgar
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024BookNet Canada
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Mattias Andersson
 
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphSIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphNeo4j
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsRizwan Syed
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr LapshynFwdays
 
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Wonjun Hwang
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machinePadma Pradeep
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationSafe Software
 
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxMaking_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxnull - The Open Security Community
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationSlibray Presentation
 
Snow Chain-Integrated Tire for a Safe Drive on Winter Roads
Snow Chain-Integrated Tire for a Safe Drive on Winter RoadsSnow Chain-Integrated Tire for a Safe Drive on Winter Roads
Snow Chain-Integrated Tire for a Safe Drive on Winter RoadsHyundai Motor Group
 
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024BookNet Canada
 

Recently uploaded (20)

CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
 
Artificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning eraArtificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning era
 
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptxE-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
 
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
 
Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024
 
APIForce Zurich 5 April Automation LPDG
APIForce Zurich 5 April  Automation LPDGAPIForce Zurich 5 April  Automation LPDG
APIForce Zurich 5 April Automation LPDG
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding Club
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?
 
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphSIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL Certs
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
 
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machine
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
 
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxMaking_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck Presentation
 
Snow Chain-Integrated Tire for a Safe Drive on Winter Roads
Snow Chain-Integrated Tire for a Safe Drive on Winter RoadsSnow Chain-Integrated Tire for a Safe Drive on Winter Roads
Snow Chain-Integrated Tire for a Safe Drive on Winter Roads
 
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
 

Study concept drift in political ontologies

  • 1. What is the problem? How can we deal with concept drift? Open questions Studying Concept Drift in Political Ontologies Shenghui Wang1,2 Stefan Schlobach1 Janet Takens2 Wouter van Atteveldt2 1 Department of Computer Science 2 Department of Communication Science Vrije Universiteit Amsterdam Workshop on Matching and Meaning 2010
  • 2. What is the problem? How can we deal with concept drift? Open questions Content analysis in Communication Science Communication scientists study all sorts of media content related to human communication Content analysis based on the NET method concepts: political actors and issues relations: associations, opinions, or actions. Example Het Openbaar Ministerie (OM) wil de komende vier jaar mensen- handel uitroeien.
  • 3. What is the problem? How can we deal with concept drift? Open questions Content analysis in Communication Science Communication scientists study all sorts of media content related to human communication Content analysis based on the NET method concepts: political actors and issues relations: associations, opinions, or actions. Example Het Openbaar Ministerie (OM) wil de komende vier jaar mensen- handel uitroeien.
  • 4. What is the problem? How can we deal with concept drift? Open questions Content analysis in Communication Science Communication scientists study all sorts of media content related to human communication Content analysis based on the NET method concepts: political actors and issues relations: associations, opinions, or actions. Example Het Openbaar Ministerie (OM) wil de komende vier jaar mensen- handel uitroeien. -1 om human trafficking
  • 5. What is the problem? How can we deal with concept drift? Open questions Semantic network analysis 2271 1067 1388 740 1373 2127 2467 1268 2351 907 1223 1739 1708 2516 1706 2393 2438 1721 1077 1052 2323 1234 1034 2394 964 1275 2120 1936 1059 1045 2221 2124 2753 2171 2653 752 2655 2054 856 693 1608 341 2647 1011 2806 1145 1625 2076 648 1386 1233 1545 329 480 361 475 845 1906 2259 883 1439 2090 1474 1332 2002 2377 1306 2077 548 654 2696 2606 2492 1635 2471 484 956 889 2199 1198 623 2614 2573 545 1409 1259 2251 1940 2751 539 1827 870 2186 2151 2423 464 1097 1841 2070 1073 1932 438 2403
  • 6. What is the problem? How can we deal with concept drift? Open questions Network-based communication science study Politicians are networking Politics is perceived by citizens via media Media study by semantic network analysis Who is determining the subjects? Who is teaming up? Who is more credible? Who owns which topic?
  • 7. What is the problem? How can we deal with concept drift? Open questions Before network analysis We first need to extract networks! How do we extract such networks? Requires: large corpora with annotated textual content Manual coding against coding books (ontologies) Automated content analysis in progress
  • 8. What is the problem? How can we deal with concept drift? Open questions Before network analysis We first need to extract networks! How do we extract such networks? Requires: large corpora with annotated textual content Manual coding against coding books (ontologies) Automated content analysis in progress
  • 9. What is the problem? How can we deal with concept drift? Open questions What is the problem? Problems with constructing annotated content Data from different time periods or genres Coded by different teams at different moments Manifesto Research Group: 25 countries, from 1945 to 2006 Comparative Policy Agendas project: media content, manifestos, legislative texts, government press statements, etc. Election campaign coverage from 1994 to 2006
  • 10. What is the problem? How can we deal with concept drift? Open questions What is the problem? Problems with constructing annotated content Data from different time periods or genres Coded by different teams at different moments Manifesto Research Group: 25 countries, from 1945 to 2006 Comparative Policy Agendas project: media content, manifestos, legislative texts, government press statements, etc. Election campaign coverage from 1994 to 2006
  • 11. What is the problem? How can we deal with concept drift? Open questions What is the problem? Problem 1: Interoperability problem while information sharing Different coding books should be merged or at least connected illegal immigration labour migrants
  • 12. What is the problem? How can we deal with concept drift? Open questions What is the problem, again? Everything changes, quickly or slowly ...
  • 13. What is the problem? How can we deal with concept drift? Open questions Follow the Fashion?
  • 14. What is the problem? How can we deal with concept drift? Open questions Women’s role? Suffragettes said that women’s role in society is unacceptable Pope says that women’s role in society is unacceptable
  • 15. What is the problem? How can we deal with concept drift? Open questions Concept drift is a problem Problem 2: Concept drift Meaning of concepts changes over time Analysis based on evolving concepts must consider temporal locality Study concept drift itself is useful
  • 16. What is the problem? How can we deal with concept drift? Open questions Datasets Five political ontologies which were used to annotate newspaper articles 23639 manually annotated newspaper articles during five recent Dutch national election campaigns There even exist manual mappings but most of them are lexically very similar
  • 17. What is the problem? How can we deal with concept drift? Open questions What are the main issues? What is concept drift? How do we detect the concept drift? How do we represent the concept drift? How do we evaluate the concept drift? How do we use the concept drift?
  • 18. What is the problem? How can we deal with concept drift? Open questions What are the main issues? What is concept drift? How do we detect the concept drift? How do we represent the concept drift? How do we evaluate the concept drift? How do we use the concept drift?
  • 19. What is the problem? How can we deal with concept drift? Open questions What are the main issues? What is concept drift? How do we detect the concept drift? How do we represent the concept drift? How do we evaluate the concept drift? How do we use the concept drift?
  • 20. What is the problem? How can we deal with concept drift? Open questions What are the main issues? What is concept drift? How do we detect the concept drift? How do we represent the concept drift? How do we evaluate the concept drift? How do we use the concept drift?
  • 21. What is the problem? How can we deal with concept drift? Open questions What are the main issues? What is concept drift? How do we detect the concept drift? How do we represent the concept drift? How do we evaluate the concept drift? How do we use the concept drift?
  • 22. What is the problem? How can we deal with concept drift? Open questions What is concept drift? Definition The meaning of concept Label Intension Extension Questions: Can three of them change at the same time? Should there be a rigid part in one concept which stays constant all the time?
  • 23. What is the problem? How can we deal with concept drift? Open questions What is concept drift? Definition The meaning of concept Label Intension Extension Questions: Can three of them change at the same time? Should there be a rigid part in one concept which stays constant all the time?
  • 24. What is the problem? How can we deal with concept drift? Open questions What is concept drift? Definition The meaning of concept Label Intension Extension Questions: Can three of them change at the same time? Should there be a rigid part in one concept which stays constant all the time?
  • 25. What is the problem? How can we deal with concept drift? Open questions What is concept drift? Definition The meaning of concept Label Intension Extension Questions: Can three of them change at the same time? Should there be a rigid part in one concept which stays constant all the time?
  • 26. What is the problem? How can we deal with concept drift? Open questions Detecting concept drift Detecting concept drift in terms of its labels its extension: instance-based mapping between different time its intension: using its hierarchical information and the co-occurrence links to other concepts of the same time
  • 27. What is the problem? How can we deal with concept drift? Open questions Representing concept drift
  • 28. What is the problem? How can we deal with concept drift? Open questions Representing concept drift: Builder’ fraud criminaliteit fiod companies,_coroprations,_business criminaliteit 0.077 0.002 bouwfraude fraude_en_corruptie 2006 0.030 0.044 0.038 bestuurlijke_vernieuwing 0.047 0.043 parlementaire_enquete_algemeen 0.154 corruptie parlementaire_enquete_bouwfrau 0.198 bouwfraude 0.034 0.097 2003 0.050 0.130 0.117 0.152 0.124 klokkenluider belangenverstrengeling jusititie 0.083 0.058 bouwfraude 2002
  • 29. What is the problem? How can we deal with concept drift? Open questions Representing concept drift: Police criminaliteit criminaliteit 0.065 0.067 0.030 criminaliteitsbestrijding 0.072 0.046 0.055 politie criminaliteit justitie 2006 0.151 0.107 0.069 politie 0.037 criminaliteit jusititie 2003 0.055 0.073 0.052 0.042 politie 0.044 rcriminaliteit xjustitie 2002 0.066 0.071 0.064 rpolitie sjo_creawetsto criminelen 0.066 0.120 1998 0.083 0.123 politie 1994
  • 30. What is the problem? How can we deal with concept drift? Open questions What kinds of concept drift can we detect?
  • 31. What is the problem? How can we deal with concept drift? Open questions What kinds of concept drift can we detect? Association shifting hervorming_politiebestel hgekozen_burgemeester 0.018 0.033 soc_vernieuwing ontwikkelingshu hbestuurlijke_vernieuwin 1998 0.082 0.074 best_vernieuwin 1994
  • 32. What is the problem? How can we deal with concept drift? Open questions What kind of concept drift can we detect? Generalising or specialising criminality 0.038 fraud and corruption corruption builder’s fraud 0.043 2006 builder’s fraud 2003
  • 33. What is the problem? How can we deal with concept drift? Open questions What kind of concept drift can we detect? Overlapping rwerkgevers lkoppeling 0.013 0.015 wgv_werkgevers rvno 0.037 0.077 1998 0.077 vno_ncw 1994
  • 34. What is the problem? How can we deal with concept drift? Open questions Open questions What other types of concept drift can we identify and automatically detect? What is an appropriate (formal) representation for the detected drift? How can we evaluate the detected concept drift, both qualitatively and quantitatively?
  • 35. What is the problem? How can we deal with concept drift? Open questions Thank you