SlideShare une entreprise Scribd logo
1  sur  20
RecSysTEL Workshop 2012
          Saarbruecken September 18, 2012




Competency Comparison Relations for
  Recommendation in Technology
   Enhanced Learning Scenarios

   Gilbert Paquette, Délia Rogozan, Olga
                   Marino
               www.licef.ca/cice

Canada Research Chair in Instructional and Cognitive
               Enginerring (CICE)
             LICEF Research Center
Background
   Add semantic references to scenario
    components: actors, tasks and resources to
    educational modeling languages such as IMS-LD
    (2003)
                             – Paquette and Marino, 2005
   “Include the improved modeling of users and
    items, and incorporation of the contextual
    information into the recommendation process”
                         – Adomavicus and Tuzhilin (2005)
   The “Adaptive Semantic Web” opens new
    approaches for recommenders systems: use of
    folksonomies and ontological filtering of resources
                                     – Jannach et al, 2011
Recommendation (assistance)
       Principles
   Epiphyte – grafted on the scenario process
    but external to it; no scenario modification
   Multi-agent system: agents are associated
    to tasks at different levels in the scenario
   Flexible association: one, some or all of the
    tasks are assisted.
   Delegation between a task agent towards its
    super tasks agents; tree topology
Insertion of recommenders
(assistance agents): an example
The implemented recommender
           model

    Recommender = {rules}
    Rule = <actor, event, condition, action >
    Event =
     –   Activity transition (started, terminated, revisited,…)
     –   Time spent (activity, global …)
     –   Resources opened, reopened,…
    Condition = boolean expression comparing:
     – Target actor progress in the scenario + knowledge and
         competencies acquired + evidence => User persistent model
     – Resources: prerequisite and target competencies
     – Activities: prerequisite and target competencies
    Action = advice, notification, model update
Semantic Referencing of
         Resources
   Of what
    – Actors, activities, documents, tools, models, scenarios …

   Why
    – Help select resources at design time for better quality scenarios
    – Inform users of the resources’ content at design or delivery time
    – Assist users according to their knowledge and competencies

   How
    – Associate formal semantic descriptors to resources from a
      domain ontologies and/or competencies based on ontology
      references
Knowledge Descriptors

Classes  and instances
    (From OWL-DL domain ontologies)
General properties:

    –Domain – Data Properties
    –Domain – ObjectProperty – Range
Instanciated properties (facts):

    –Instance – Property
    –Instance – Property – Value
Competency Descriptors

   Knowledge descriptors

   Competency descriptors
    – (K, S, P) triples
          K: Knowledge descriptor
                                                           K=Planet
                                                           K=Planet
            – From a OWL domain ontology
          S: Generic Skill
                                                           S=Apply
                                                           S=Apply
            – From a 10-level taxonomy (Paquette, 2007)
          P: Performance level
                                                           P=Expert
                                                           P=Expert
            – A combination of P-values (Paquette, 2007)
Referencing Process in the
     TELOS Implementation
     Ontology          Resource        Semantic
1
1    contruction   2
                   2   selection   3
                                   3   Referencing
     or import                         Of resources




      … and/or
    competencies
Semantic Search Methods

        Type de recherche                 Type de résultat
Simple                                  Exact match
Using key words from the ontology


Advanced                                Exact match
Using knowledge and competency          Semantically
boolean query                           near match
                                        Exact match
Resource Pairing
                                        Semantically
Using semantic comparison between
queried ressource and other resources   near match
             → Rests on knowledge and competency comparison
Knowledge Comparison
                        (K1 et K2)


   Based on the structure of the ontology where the
    knowledge descriptors are stored
   Compare the neighbourhoods of K1 and K2




   Possible results
     – K2 near and more specialized / general than K1
Competency Comparison
           C1=(K1, S1, P1) et C2=(K2, S2, P2)


   Based on knowledge comparison (K)
   Base on the distance between skills’ levels (H) and
    performance levels distances(P)


   Possible results
     C2 veryNear / Near C1

     C2 stronger / weaker than C1

     C2 more specialized / general than C1
Competency Comparison
Competency comparison
       within rule conditions
   A competency-based condition is a triple:
    – ObjectCompetencyList is the list of prerequisite or
      target competencies of another actor, a task or a
      resource to be compared with user’s actual
      competency list
    – Relation is one of the comparison relations :
       Identical, Near, VeryNear, MoreGeneric, MoreSpecific,
       Stronger, Weaker, or any combination of these.
    – Quantification takes two values: HasOne or HasAll

   EX: HasAll /NearMoreSpecific / Target competencies for Essay
   EX: HasOne/Weaker/Target competency for Build Table activity
Recommendation example
Notification example
User model update
Achievements in this project
   Extension of the TELOS Technical Ontology for
    semantic referencing of resources, search and
    recommendation
   Definition of a Typology of semantic descriptors
    (ontology descriptors and competenciers)
   Search methods for resources ‘identical’ ou ‘near’
    sémantically
   Recommendation Model: based on competency
    comparison between actors, tasks and resources
   New integrated suite of tools: Semantic referencer,
    Semantic search tools, Competency and Ontology
    editors, Integration to recommanders scenarios,
    Recomenders’ rule editor.
Future steps
   More experimental validation to refine the semantic relations
    between OWL-DL references, i.e adding weights to the various
    comparison cases
   Investigate recommendation methods for groups in
    collaborative scenarios (permitted by our model of multi-actor
    learning scenarios)
   Improve the practical use of the approach, partly automate
    tasks, improve the ergonomics
   Investigate the integration of other recommendation methods
    (e.g. user analytics)
   “Free” the suite of tools from TELOS to extend its usability on
    the Web of data.
RecSysTEL Workshop 2012
          Saarbruecken September 18, 2012




                 Questions ?
                 Comments ?

   Gilbert Paquette, Délia Rogozan, Olga
                     Marino
        www.licef.ca/cice; www.licef.ca/gp



Canada Research Chair in Instructional and Cognitive
               Enginerring (CICE)
             LICEF Research Center

Contenu connexe

Similaire à Rec systel 2012 competency based recommendation

An adaptive Multi-Agent based Architecture for Engineering Education
An adaptive Multi-Agent based Architecture for Engineering EducationAn adaptive Multi-Agent based Architecture for Engineering Education
An adaptive Multi-Agent based Architecture for Engineering Education
Miguel R. Artacho
 
Extending Recommendation Systems With Semantics And Context Awareness
Extending Recommendation Systems With Semantics And Context AwarenessExtending Recommendation Systems With Semantics And Context Awareness
Extending Recommendation Systems With Semantics And Context Awareness
Victor Codina
 
Repositories and the wider context
Repositories and the wider contextRepositories and the wider context
Repositories and the wider context
Julie Allinson
 
kantorNSF-NIJ-ISI-03-06-04.ppt
kantorNSF-NIJ-ISI-03-06-04.pptkantorNSF-NIJ-ISI-03-06-04.ppt
kantorNSF-NIJ-ISI-03-06-04.ppt
butest
 
C-SAP e-learning forum: Overview of Open Educational Resources project
C-SAP e-learning forum: Overview of Open Educational Resources projectC-SAP e-learning forum: Overview of Open Educational Resources project
C-SAP e-learning forum: Overview of Open Educational Resources project
CSAPSubjectCentre
 
Paper presentations: UK e-science AHM meeting, 2005
Paper presentations: UK e-science AHM meeting, 2005Paper presentations: UK e-science AHM meeting, 2005
Paper presentations: UK e-science AHM meeting, 2005
Paolo Missier
 

Similaire à Rec systel 2012 competency based recommendation (20)

The Role Of Ontology In Modern Expert Systems Dallas 2008
The Role Of Ontology In Modern Expert Systems   Dallas   2008The Role Of Ontology In Modern Expert Systems   Dallas   2008
The Role Of Ontology In Modern Expert Systems Dallas 2008
 
Semantic Relatedness of Web Resources by XESA - Philipp Scholl
Semantic Relatedness of Web Resources by XESA - Philipp SchollSemantic Relatedness of Web Resources by XESA - Philipp Scholl
Semantic Relatedness of Web Resources by XESA - Philipp Scholl
 
Keynote at AgroLT 2008
Keynote at AgroLT 2008Keynote at AgroLT 2008
Keynote at AgroLT 2008
 
3rd Workshop on Social Information Retrieval for Technology-Enhanced Learnin...
3rd Workshop onSocial  Information Retrieval for Technology-Enhanced Learnin...3rd Workshop onSocial  Information Retrieval for Technology-Enhanced Learnin...
3rd Workshop on Social Information Retrieval for Technology-Enhanced Learnin...
 
Sirtel Workshop
Sirtel WorkshopSirtel Workshop
Sirtel Workshop
 
An adaptive Multi-Agent based Architecture for Engineering Education
An adaptive Multi-Agent based Architecture for Engineering EducationAn adaptive Multi-Agent based Architecture for Engineering Education
An adaptive Multi-Agent based Architecture for Engineering Education
 
Open IE tutorial 2018
Open IE tutorial 2018Open IE tutorial 2018
Open IE tutorial 2018
 
Semantics in Financial Services -David Newman
Semantics in Financial Services -David NewmanSemantics in Financial Services -David Newman
Semantics in Financial Services -David Newman
 
Extending Recommendation Systems With Semantics And Context Awareness
Extending Recommendation Systems With Semantics And Context AwarenessExtending Recommendation Systems With Semantics And Context Awareness
Extending Recommendation Systems With Semantics And Context Awareness
 
Resource Description Framework Approach to Data Publication and Federation
Resource Description Framework Approach to Data Publication and FederationResource Description Framework Approach to Data Publication and Federation
Resource Description Framework Approach to Data Publication and Federation
 
Repositories and the wider context
Repositories and the wider contextRepositories and the wider context
Repositories and the wider context
 
kantorNSF-NIJ-ISI-03-06-04.ppt
kantorNSF-NIJ-ISI-03-06-04.pptkantorNSF-NIJ-ISI-03-06-04.ppt
kantorNSF-NIJ-ISI-03-06-04.ppt
 
OER2011: Tacit models of resource creation
OER2011: Tacit models of resource creationOER2011: Tacit models of resource creation
OER2011: Tacit models of resource creation
 
2016-05-31 Venia Legendi (CEITER): Sergey Sosnovsky
2016-05-31 Venia Legendi (CEITER): Sergey Sosnovsky2016-05-31 Venia Legendi (CEITER): Sergey Sosnovsky
2016-05-31 Venia Legendi (CEITER): Sergey Sosnovsky
 
Orchestrating collaborative technology-enhanced ecosystems: How to support te...
Orchestrating collaborative technology-enhanced ecosystems: How to support te...Orchestrating collaborative technology-enhanced ecosystems: How to support te...
Orchestrating collaborative technology-enhanced ecosystems: How to support te...
 
Supporting Flexible Competency Frameworks
Supporting Flexible Competency FrameworksSupporting Flexible Competency Frameworks
Supporting Flexible Competency Frameworks
 
Overview of C-SAP open educational resources project
Overview of C-SAP open educational resources projectOverview of C-SAP open educational resources project
Overview of C-SAP open educational resources project
 
C-SAP e-learning forum: Overview of Open Educational Resources project
C-SAP e-learning forum: Overview of Open Educational Resources projectC-SAP e-learning forum: Overview of Open Educational Resources project
C-SAP e-learning forum: Overview of Open Educational Resources project
 
Using Semantic Analysis for Content Alignment &amp; Gap Analysis
Using Semantic Analysis for Content Alignment &amp; Gap AnalysisUsing Semantic Analysis for Content Alignment &amp; Gap Analysis
Using Semantic Analysis for Content Alignment &amp; Gap Analysis
 
Paper presentations: UK e-science AHM meeting, 2005
Paper presentations: UK e-science AHM meeting, 2005Paper presentations: UK e-science AHM meeting, 2005
Paper presentations: UK e-science AHM meeting, 2005
 

Plus de Gilbert Paquette

Les CLOM (MOOC), les compétences et la personnalisation des apprentissage: la...
Les CLOM (MOOC), les compétences et la personnalisation des apprentissage: la...Les CLOM (MOOC), les compétences et la personnalisation des apprentissage: la...
Les CLOM (MOOC), les compétences et la personnalisation des apprentissage: la...
Gilbert Paquette
 

Plus de Gilbert Paquette (20)

Aggrégation des rel (hammamet, nov 2017) [enregistré automatiquement]
Aggrégation des rel (hammamet, nov 2017) [enregistré automatiquement]Aggrégation des rel (hammamet, nov 2017) [enregistré automatiquement]
Aggrégation des rel (hammamet, nov 2017) [enregistré automatiquement]
 
Émergence de liens sémantiques à partir du marquage social
Émergence de liens sémantiques à partir du marquage socialÉmergence de liens sémantiques à partir du marquage social
Émergence de liens sémantiques à partir du marquage social
 
L'ingénierie des ENA fondée sur le web des données ouvertes et liées
L'ingénierie des ENA fondée sur le web des données ouvertes et liéesL'ingénierie des ENA fondée sur le web des données ouvertes et liées
L'ingénierie des ENA fondée sur le web des données ouvertes et liées
 
Le partage des ressources éducatives dans la francophonie (avril 2016)
Le partage des ressources éducatives dans la francophonie (avril 2016)Le partage des ressources éducatives dans la francophonie (avril 2016)
Le partage des ressources éducatives dans la francophonie (avril 2016)
 
Le Web sémantique pour la formation et la gestion des connaissances dans les ...
Le Web sémantique pour la formation et la gestion des connaissances dans les ...Le Web sémantique pour la formation et la gestion des connaissances dans les ...
Le Web sémantique pour la formation et la gestion des connaissances dans les ...
 
Conf.journée licef 2016
Conf.journée licef 2016Conf.journée licef 2016
Conf.journée licef 2016
 
Opening up MOOCs for OER management on the Web of linked data
Opening up MOOCs for OER management on the Web of linked dataOpening up MOOCs for OER management on the Web of linked data
Opening up MOOCs for OER management on the Web of linked data
 
Bejaoui r., paquette g., basque j. et henri f. comment personnaliser l'appren...
Bejaoui r., paquette g., basque j. et henri f. comment personnaliser l'appren...Bejaoui r., paquette g., basque j. et henri f. comment personnaliser l'appren...
Bejaoui r., paquette g., basque j. et henri f. comment personnaliser l'appren...
 
Comete 08-07-14
Comete   08-07-14Comete   08-07-14
Comete 08-07-14
 
Les CLOM (MOOC), les compétences et la personnalisation des apprentissage: la...
Les CLOM (MOOC), les compétences et la personnalisation des apprentissage: la...Les CLOM (MOOC), les compétences et la personnalisation des apprentissage: la...
Les CLOM (MOOC), les compétences et la personnalisation des apprentissage: la...
 
Les CLOM/MOOC et les modèles pédagogiques de formation en ligne.
Les CLOM/MOOC et les modèles pédagogiques de formation en ligne.Les CLOM/MOOC et les modèles pédagogiques de formation en ligne.
Les CLOM/MOOC et les modèles pédagogiques de formation en ligne.
 
Comete 08-07-14
Comete   08-07-14Comete   08-07-14
Comete 08-07-14
 
Des ressources éducatives libres aux MOOC : Défis et orientations
Des ressources éducatives libres aux MOOC : Défis et orientationsDes ressources éducatives libres aux MOOC : Défis et orientations
Des ressources éducatives libres aux MOOC : Défis et orientations
 
Oif atelier rel - moncton 4-8.02.13
Oif atelier rel - moncton 4-8.02.13Oif atelier rel - moncton 4-8.02.13
Oif atelier rel - moncton 4-8.02.13
 
Priows présentation des résultats
Priows présentation des résultats Priows présentation des résultats
Priows présentation des résultats
 
Notion opérationnelle de compétence - référencement sémantique et assisance a...
Notion opérationnelle de compétence - référencement sémantique et assisance a...Notion opérationnelle de compétence - référencement sémantique et assisance a...
Notion opérationnelle de compétence - référencement sémantique et assisance a...
 
Contenu d'un nouveau cours sur les Technologies sémantiques
Contenu d'un nouveau cours sur les Technologies sémantiquesContenu d'un nouveau cours sur les Technologies sémantiques
Contenu d'un nouveau cours sur les Technologies sémantiques
 
Modèles et métadonnées pour les scénarios pédagogiques
Modèles et métadonnées pour les scénarios pédagogiquesModèles et métadonnées pour les scénarios pédagogiques
Modèles et métadonnées pour les scénarios pédagogiques
 
Présentation sur les ressources ouvertes et les licences Creative Commons
Présentation sur les ressources ouvertes et les licences Creative CommonsPrésentation sur les ressources ouvertes et les licences Creative Commons
Présentation sur les ressources ouvertes et les licences Creative Commons
 
Présentation du projet REFRER sur les référentiels de ressources éducatives r...
Présentation du projet REFRER sur les référentiels de ressources éducatives r...Présentation du projet REFRER sur les référentiels de ressources éducatives r...
Présentation du projet REFRER sur les référentiels de ressources éducatives r...
 

Rec systel 2012 competency based recommendation

  • 1. RecSysTEL Workshop 2012 Saarbruecken September 18, 2012 Competency Comparison Relations for Recommendation in Technology Enhanced Learning Scenarios Gilbert Paquette, Délia Rogozan, Olga Marino www.licef.ca/cice Canada Research Chair in Instructional and Cognitive Enginerring (CICE) LICEF Research Center
  • 2. Background  Add semantic references to scenario components: actors, tasks and resources to educational modeling languages such as IMS-LD (2003) – Paquette and Marino, 2005  “Include the improved modeling of users and items, and incorporation of the contextual information into the recommendation process” – Adomavicus and Tuzhilin (2005)  The “Adaptive Semantic Web” opens new approaches for recommenders systems: use of folksonomies and ontological filtering of resources – Jannach et al, 2011
  • 3. Recommendation (assistance) Principles  Epiphyte – grafted on the scenario process but external to it; no scenario modification  Multi-agent system: agents are associated to tasks at different levels in the scenario  Flexible association: one, some or all of the tasks are assisted.  Delegation between a task agent towards its super tasks agents; tree topology
  • 5. The implemented recommender model  Recommender = {rules}  Rule = <actor, event, condition, action >  Event = – Activity transition (started, terminated, revisited,…) – Time spent (activity, global …) – Resources opened, reopened,…  Condition = boolean expression comparing: – Target actor progress in the scenario + knowledge and competencies acquired + evidence => User persistent model – Resources: prerequisite and target competencies – Activities: prerequisite and target competencies  Action = advice, notification, model update
  • 6. Semantic Referencing of Resources  Of what – Actors, activities, documents, tools, models, scenarios …  Why – Help select resources at design time for better quality scenarios – Inform users of the resources’ content at design or delivery time – Assist users according to their knowledge and competencies  How – Associate formal semantic descriptors to resources from a domain ontologies and/or competencies based on ontology references
  • 7. Knowledge Descriptors Classes and instances (From OWL-DL domain ontologies) General properties: –Domain – Data Properties –Domain – ObjectProperty – Range Instanciated properties (facts): –Instance – Property –Instance – Property – Value
  • 8. Competency Descriptors  Knowledge descriptors  Competency descriptors – (K, S, P) triples  K: Knowledge descriptor K=Planet K=Planet – From a OWL domain ontology  S: Generic Skill S=Apply S=Apply – From a 10-level taxonomy (Paquette, 2007)  P: Performance level P=Expert P=Expert – A combination of P-values (Paquette, 2007)
  • 9. Referencing Process in the TELOS Implementation Ontology Resource Semantic 1 1 contruction 2 2 selection 3 3 Referencing or import Of resources … and/or competencies
  • 10. Semantic Search Methods Type de recherche Type de résultat Simple Exact match Using key words from the ontology Advanced Exact match Using knowledge and competency Semantically boolean query near match Exact match Resource Pairing Semantically Using semantic comparison between queried ressource and other resources near match → Rests on knowledge and competency comparison
  • 11. Knowledge Comparison (K1 et K2)  Based on the structure of the ontology where the knowledge descriptors are stored  Compare the neighbourhoods of K1 and K2  Possible results – K2 near and more specialized / general than K1
  • 12. Competency Comparison C1=(K1, S1, P1) et C2=(K2, S2, P2)  Based on knowledge comparison (K)  Base on the distance between skills’ levels (H) and performance levels distances(P)  Possible results  C2 veryNear / Near C1  C2 stronger / weaker than C1  C2 more specialized / general than C1
  • 14. Competency comparison within rule conditions  A competency-based condition is a triple: – ObjectCompetencyList is the list of prerequisite or target competencies of another actor, a task or a resource to be compared with user’s actual competency list – Relation is one of the comparison relations : Identical, Near, VeryNear, MoreGeneric, MoreSpecific, Stronger, Weaker, or any combination of these. – Quantification takes two values: HasOne or HasAll  EX: HasAll /NearMoreSpecific / Target competencies for Essay  EX: HasOne/Weaker/Target competency for Build Table activity
  • 18. Achievements in this project  Extension of the TELOS Technical Ontology for semantic referencing of resources, search and recommendation  Definition of a Typology of semantic descriptors (ontology descriptors and competenciers)  Search methods for resources ‘identical’ ou ‘near’ sémantically  Recommendation Model: based on competency comparison between actors, tasks and resources  New integrated suite of tools: Semantic referencer, Semantic search tools, Competency and Ontology editors, Integration to recommanders scenarios, Recomenders’ rule editor.
  • 19. Future steps  More experimental validation to refine the semantic relations between OWL-DL references, i.e adding weights to the various comparison cases  Investigate recommendation methods for groups in collaborative scenarios (permitted by our model of multi-actor learning scenarios)  Improve the practical use of the approach, partly automate tasks, improve the ergonomics  Investigate the integration of other recommendation methods (e.g. user analytics)  “Free” the suite of tools from TELOS to extend its usability on the Web of data.
  • 20. RecSysTEL Workshop 2012 Saarbruecken September 18, 2012 Questions ? Comments ? Gilbert Paquette, Délia Rogozan, Olga Marino www.licef.ca/cice; www.licef.ca/gp Canada Research Chair in Instructional and Cognitive Enginerring (CICE) LICEF Research Center

Notes de l'éditeur

  1. Donner des exemples (à l ’oral) pour chaque type de recherche.
  2. Voisinage ‘proche’ au sens qu’on ne descend pas la hiérarchie des classes, propriétés, etc.…