1. Exploiting Semantic Web and Knowledge Management Technologies for E-learning
Sylvain Dehors
Director
Rose Dieng-Kuntz
INRIA Sophia Antipolis
University of Nice-Sophia Antipolis/ ED STIC

2. E-learning, this ?

3. A vision of e-learning For us:
Any learning activity mediated by a computer
Buzz Word, but also real change in practices
Use of computers in daily activities
All ages, from youngster to adult teaching
In practice, several types of application
Simulation programs
Tutoring systems
On-line courses
In the context of learning we are primarily interested in knowledge communication, but as we’ll see other aspects are important
E-learning = broad term
Connection with KM very natural

4. Our e-learning situation
Learning organization
Teacher(s) with a group of students
Environment
Computers for daily usage
Either on-line or face-to-face
Knowledge Sources
Course documents
Teacher’s expertise
Provide computer support for taking advantage of the knowledge sources

5. Outline Research question Method Proposal Conclusion
Selection and analysis of existing material
Semi automatic annotation
Learning activity
Analysis
Conclusion

6. Research question Proposal:
How can teachers and students better use knowledge sources, such as pedagogical documents, with computer interfaces ?
Proposal:
apply Knowledge Management techniques and Semantic Web technology
develop a practical method
Illustration: a tool (QBLS) and experiments

7. Inspirations Knowledge Management Semantic Web:
“The objective of a knowledge management structure is to promote knowledge growth, promote knowledge communication, and in general preserve knowledge within the organisation” (Steels L., 93)
Semantic Web:
“The Semantic Web provides a common framework that allows data to be shared across application, enterprise, and common boundaries.” (W3C)
Standards: RDF, RDFS, OWL, SPARQL

8. Existing methods and tools (Dieng et al.)
Corporate semantic web
Knowledge holder DB
documents
services
Semantic
annotation
base
ontologies
Knowledge Management Syst.
edit O
edit A
query
User (collective task)
User (Individual task)
Apply to a learning organization
- Tool: Corese semantic search engine to query formalized knowledge
W3C Standards expressing knowledge about the course

9. Method description 2
1 - Selection and analysis of existing material
2 - Semi automatic annotation 1 4 3
3 - Learning activity
4 - Analysis

10. Conceptual navigation
Method description
Select
Enrich 2 1
Original resources
selection
KM tools
Semantization 4 3
Ontologies :
Document
Pedagogy
Domain
Usage feedback
tests
Annotations
Activity analysis
Use
Conceptual navigation
+ adaptation
Analyze

11. Experiment’s Agenda QBLS-2 : QBLS-1 : QBLS-ASPL : 3 months course
2 hours lab
Signal Analysis
QBLS-2 :
3 months course
Java Programming
QBLS-ASPL :
Knowledge Web NoE
Semantic Web studies
2005
2006
2007

12. Resource selection First, establish a pedagogical strategy
Collaboration Teacher/QBLS designer
QBLS: Question Based Learning Strategy: Motivation, autonomy, self-directed learning
Existing resources:
Objective criteria
Availability, standard editable format (XML)
Suitability for annotation (modularity, coherence, vocabulary used)
Subjective criteria
Scope, goal, context
Teacher’s acceptance
Mostly human process

13. Original documents Power Point presentations Modularity
Signal analysis / Java programming
Used as hard copy course material
Two different experiments:
One on an original subject : signal processing
One on a classic subject for comparison with other approaches : JAVA programming
Modularity
Coherence, Vocabulary

14. Ontology selection Selection of existing models, ontologies? Document:
Must fit the course structure
Document organization Document ontology
Pedagogy:
Appropriate for the pedagogical approach
Domain to learn:
Usually the biggest ontology
Fit the document contents (vocabulary used, conceptualization)
Fit the teacher’s vision
Lots of constraints, difficult to find appropriate ontologies

15. 1- Selection and analysis of existing material
2 – Semi automatic annotation
4 - Analysis
3 – Learning activity

16. Annotation Express additional knowledge about the course Principles :
Based on teacher’s expertise and vision
Principles :
Use existing edition tools
Proceed through visual mark-up
Rely on XML technologies and Semantic Web formalisms
3 key principles that are crucial for annotation (both from literature review and experience)
3 steps

17. A semi-automatic process
3 steps
Pre-processing
Manual annotation
Automatic extraction
resource to reuse
(XML)
“annotable” version
annotated version
content
(XHTML)
annotation
(RDF)
pre-processing
manual annotation
xsl transform.
Ontologies (OWL, RDFS)

18. Preprocessing Identification of the content characteristics
Separation in small entities
Automatic annotation
Vocabulary used → domain concepts, automatic annotation with domain ontology
Resource roles → pedagogical ontology
Preparation
Styles → reflect ontological concepts
enrich style lists with ontologies
Other indicators usually employed in resource management: date, course, author.

19. Preprocessing

20. Preprocessing <draw:page draw:name="Fundamental concepts">
<draw:text-box>
<text:p> Fundamental concepts</text:p>
</draw:text-box>
<text:unordered-list>
<text:list-item>
<text:p text:style-name="P19">object</text:p>
</text:list-item>
<text:p text:style-name="P19">class</text:p>
</text:unordered-list>
...
</draw:page>
<draw:page draw:name="Objects and classes">
<draw:text-box>...
<text:p> Objects and classes</text:p>
</draw:text-box>
<draw:text-box>
<text:unordered-list>
<text:list-item>
<text:p>objects</text:p>
</text:list-item>
</text:unordered-list>
...
</draw:page>
<draw:page draw:name="Methods and parameters">
<draw:text-box>
<text:p> Methods and parameters </text:p>
</draw:text-box>
<text:unordered-list>
<text:list-item>
<text:p> objects have operations which can be
invoked (Java calls them methods) </text:p>
</text:list-item>
<text:p> methods may have parameters to pass
additional information needed to execute </text:p>
</text:unordered-list>
</draw:page>

21. Preprocessing

22. Preprocessing
Ici indiquer pas de lemmatisation mais pluriels/singuliers

23. Manual annotation
Exploitation of tools functionalities by the teacher for a visual markup
Evolution/enrichment/creation of corresponding domain ontology
Practical objective: connecting navigation paths
Edition of the content
Linking concepts with semantic hierarchical relations (SKOS)
Statement
Interface
skos:broader
skos:broader
skos:broader
Conditional
Statement
Assignment
Statement
Keyword « implements »

24. Final result: Open Office-Writer

25. Final result : MS-Word

26. Experimental results: ontology re-use
Pedagogical ontology
Reused directly
Same intention as original: describe ped. role (generic?)
Domain Ontology
Design intention very important: here offer “conceptual views” of the resources
Mostly developed specifically, comparisons with other domain ontologies show striking incompatibilities.
Method modifiers
Access rights
public
protected
private
public
protected
private

27. Experimental results: annotation cost
QBLS-1
QBLS-2
Number of resources 92
359
Num. of resources discarded
None 54
Course duration 2H
3 months
Number of pedagogical types used (directly)
8/8
12/27
Num. of domain concepts 41
171
Editing Tool
Microsoft Word
OpenOffice Writer
Annotation time
N/A
20H
Modification of content
Yes No

28. 1- Selection and analysis of existing material
2 – Semi automatic annotation
4 - Analysis
3 – learning activity

29. Learning activity
Offer “conceptual” navigation in the set of resources while answering questions or performing exercises
Navigation through semantic queries
Take advantage of domain concepts hierarchy (broader links)
Use typology of pedagogical concepts for ordering (subsumption)
Interface generation
Static XSL style sheets: performance, reuse, maintenance

30. Semantic Web architecture
Domain vocabulary
Pedagogical ontology
Doc. model
Corese
Semantic
Search Engine
(RDFS)
(Skos)
(OWL)
rules
logs
(RDF) 4
Formalized Knowledge 3
Answers
(Sparql-XML)
Queries
(Sparql)
web-app
content
(XHTML)
XSLT
Learner
Interface
(XHTML) 2 5
Request 6
Tomcat web server
HTTP 1

31. Semantic Web at work Dynamic SPARQL queries: Variable SELECT * WHERE {
skos:primarySubject
skos:broader
SELECT * WHERE {
FILTER (?c = java:variable)
{ ?doc skos:primarySubject ?c }
UNION
{ ?doc skos:primarySubject ?c2 . ?c2 skos:broader ?c}
?doc rdf:type ?t
?t edu:order ?order
?doc dc:title ?docTitle
?t rdfs:label ?docLab
?c skos:prefLabel ?cLab }
ORDER BY ?order
Local
Variable
skos:primarySubject
rdf:type
Definition
?doc edu:belongsTo java:Chapter1
?doc skos:subject ?ext_concept
FILTER{ ?ext_doc skos:primirySubject ?ext_concept OR
{?ext_doc skos:primirySubject ?c2 . ?c2 skos:broader ?ext_concept}}
edu:order
rdf:type
Layout information
Example 3
edu:order 7

32. Semantic Web at work(2) Refining the query Contextual information
User adaptation
?doc skos:subject ?ext_concept
{ ?ext_doc skos:primirySubject ?ext_concept }
UNION
{ ?ext_doc skos:primirySubject ?c2 . ?c2 skos:broader ?ext_concept }
?ext-doc edu:belongsTo java:Chapter1
OPTIONAL { FILTER (?user = epu:user1)
?user edu:profile ?profile
?profile edu:orderingRelationType ?p
?t ?p ?order }

33. QBLS-1
Simple conceptual navigation
Question Based Navigation

34. QBLS-2 Human readable information Variable Fields Local variable
skos:broader
Fields
Local variable

35. Experimental results: students’ feedback
QBLS-1
QBLS-2
Num. of students using the system
100%
30%
Num. of resources visited
90%
80%
Overall Satisfaction
4.3/5
3.9/5
Off-hours access
N/A
50% of connections
Good satisfaction
Structured navigation appreciated for direct access to information
Use of domain and pedagogical information

36. QBLS-ASPL (Advanced Semantic Platform for Learning)
Existing resources on a portal : REASE,
MS-PowerPoint files

37. QBLS-ASPL
Interesting Web sites for advanced learners

38. QBLS-ASPL
Provided by QBLS

39. 1- Selection and analysis of existing material
2 – Semi automatic annotation
4 - Analysis
3 – Exploitation by learners

40. Analysis Modeling user activity Exploitation of logs
A navigation model based on a graph representation
Exploitation of logs
Visualization through automatically generated graphs
Use semantic querying to highlight particular characteristics of the graphs represented in RDF
Concept
subject of
mentions
Concept
subject of
Resource
Resource
User A
Time t

41. Visualization

42. Visualization

43. Semantic querying Find regularities, patterns?
Using the graph structure
Relying on the ontology
SELECT ?user count ?v WHERE {
?aux skos:primarySubject ?concept
?aux rdf:type edu:Auxilliary
?v edu:user ?user
?v edu:conceptVisited ?concept
OPTIONAL { ?v2 edu:resourceVisited ?aux
?v2 edu:user ?user}
FILTER(! bound(?v2)) } ?v
Show the interest of graph based vision of RDF + semantics
Object
?v2
Def
Ex.

44. Experimental Results Involve teacher’s in the analysis
Problem with large size graphs
Visualization tools not sufficient yet
Needs to be coupled with other sources of information
First step towards automated interpretation
Define a collection of patterns -> behavioral patterns
Use in “real-time”?

45. Conclusion Semantic Web = valid connector Learning Object Repositories
LOM standard
Scorm?
Annotation tools
Linguistic analysis
How it fits all together
A coherent and complete method but only few pieces of the global picture
Learner modeling
Activity tracking
Learning Design
Adaptive hypermedia
Semantic Web = valid connector

46. Conclusion (2) Semantic web interests: Ontologies for e-learning
Existing tools, Corese, Protégé, etc.
Existing models, in standard language
Unification and connection with other systems
Ontologies for e-learning
Interest, reusability of domain might be limited
Need for simple expressivity, “goal oriented design”

47. Conclusion(3) Resource Reuse Knowledge management approach
Observed use and good satisfaction level
Definite interest, cost still high
Knowledge management approach
Satisfaction of users
Initial goal fulfilled
May apply to other learning contexts

48. Perspectives (1) Short term Middle term
Further develop annotation system based on existing tools
Administrative tools to make teachers fully autonomous
Middle term
Enhance scalability with large RDF bases ( when triples are generated by learner activity)
Generalize log visualization, work on usage of such representations (e.g. teachers’ interpretations)

49. Perspectives (2) Long term
Investigate the cognitive implications for learning of the annotations
Importance of the pedagogical concepts
Structure of the domain
Enhance user tracking (more information, refine model)
All the tools are now there for extensive cognitive experiments.

50. Acknowledgements Catherine Faron-Zucker Jean Paul Stromboni
Peter Sander