tencompetence workshop - stimulating personal development and knowledge sharingoctober, 30-31, 2008,...

19
TENCompetence Workshop - Stimulating Personal Development and Knowledge Shari ng October, 30-31, 2008, Sofia, Bulg aria 1 A formal approach to adaptive content delivery Dessislava Vassileva, Department of Inf. Technologies, Sofia University “St. Kliment Ohridski”, BULGARIA

Upload: gabriel-bell

Post on 05-Jan-2016

213 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: TENCompetence Workshop - Stimulating Personal Development and Knowledge SharingOctober, 30-31, 2008, Sofia, Bulgaria1 A formal approach to adaptive content

TENCompetence Workshop - Stimulating Personal Development and Knowledge Sharing October, 30-31, 2008, Sofia, Bulgaria 1

A formal approach to adaptive content delivery

Dessislava Vassileva,Department of Inf. Technologies, Sofia University “St. Kliment Ohridski”, BULGARIA

Page 2: TENCompetence Workshop - Stimulating Personal Development and Knowledge SharingOctober, 30-31, 2008, Sofia, Bulgaria1 A formal approach to adaptive content

TENCompetence Workshop - Stimulating Personal Development and Knowledge Sharing October, 30-31, 2008, Sofia, Bulgaria 2

Agenda

• Introduction to adaptive e-learning systems

• A triangular model of Adaptive hypermedia systems (AHS)

• Adaptation engine UML activity diagram• Formal specification of AHS• Future works

Page 3: TENCompetence Workshop - Stimulating Personal Development and Knowledge SharingOctober, 30-31, 2008, Sofia, Bulgaria1 A formal approach to adaptive content

TENCompetence Workshop - Stimulating Personal Development and Knowledge Sharing October, 30-31, 2008, Sofia, Bulgaria 3

Introduction to adaptive e-learning systems

• Definition– attempt to be different for different students and groups of

students – attempt to be more adaptive by building a model of the goals,

preferences, knowledge and performance of each individual student (user/learner model) and using this model throughout the interaction with the student in order to adapt to the needs of that student

• Techniques for adaptation: adaptive navigation – link hiding, sorting, annotation adaptive presentation - content of a page according to

learner’s knowledge, goals, preferences, performance and etc. adaptive content selection – show, sort or hide search result

content adaptive problem solution

Page 4: TENCompetence Workshop - Stimulating Personal Development and Knowledge SharingOctober, 30-31, 2008, Sofia, Bulgaria1 A formal approach to adaptive content

TENCompetence Workshop - Stimulating Personal Development and Knowledge Sharing October, 30-31, 2008, Sofia, Bulgaria 4

A conceptual model of AHS

Page 5: TENCompetence Workshop - Stimulating Personal Development and Knowledge SharingOctober, 30-31, 2008, Sofia, Bulgaria1 A formal approach to adaptive content

TENCompetence Workshop - Stimulating Personal Development and Knowledge Sharing October, 30-31, 2008, Sofia, Bulgaria 5

• Learner model consist of three sub-models: Learning goals and preferences Learning style - such as visual, auditory,

kinesthetic and others styles; described in a declarative manner and determined in the very beginning of the learning by appropriate tests

Learner’s knowledge & performance

Learner model

Page 6: TENCompetence Workshop - Stimulating Personal Development and Knowledge SharingOctober, 30-31, 2008, Sofia, Bulgaria1 A formal approach to adaptive content

TENCompetence Workshop - Stimulating Personal Development and Knowledge Sharing October, 30-31, 2008, Sofia, Bulgaria 6

Domain model

• Domain model - presented by:content itself - granulized in LO according the

SCORM standardmetadata – Learning Object Metadata (LOM) can

be described according the LMS LOM specification

Ontology threesDomain1 Domain2 Domain3

LO11 LO12 LO13 LO21 LO31 LO32

Page 7: TENCompetence Workshop - Stimulating Personal Development and Knowledge SharingOctober, 30-31, 2008, Sofia, Bulgaria1 A formal approach to adaptive content

TENCompetence Workshop - Stimulating Personal Development and Knowledge Sharing October, 30-31, 2008, Sofia, Bulgaria 7

Adaptation model

• Adaptation model includes: Narrative storyboard

(graph, CP, pages) Link annotation, exam thresholds Storyboard

rules - it used for controlling the e-learning process.

WP2

WP1

WP3

CP1 CP2

P1 P5P6

P2

P4P3P7

Page 8: TENCompetence Workshop - Stimulating Personal Development and Knowledge SharingOctober, 30-31, 2008, Sofia, Bulgaria1 A formal approach to adaptive content

TENCompetence Workshop - Stimulating Personal Development and Knowledge Sharing October, 30-31, 2008, Sofia, Bulgaria 8

Adaptive engine

• Manipulate link annotation• Show/hide fragments of the pages’ content• Select of the best storyboard graph’s arc according

to adaptation rules and learner model• Update learner profile – knowledge, performance

based on learners’ test results

Page 9: TENCompetence Workshop - Stimulating Personal Development and Knowledge SharingOctober, 30-31, 2008, Sofia, Bulgaria1 A formal approach to adaptive content

TENCompetence Workshop - Stimulating Personal Development and Knowledge Sharing October, 30-31, 2008, Sofia, Bulgaria 9

Adaptation engine UML activity diagram

• The adaptation engine’s main activities include: Finding the best path Delivering appropriate

link annotation and page content

Generating learner’s test

Updating paths’ weight and learner profile

Page 10: TENCompetence Workshop - Stimulating Personal Development and Knowledge SharingOctober, 30-31, 2008, Sofia, Bulgaria1 A formal approach to adaptive content

TENCompetence Workshop - Stimulating Personal Development and Knowledge Sharing October, 30-31, 2008, Sofia, Bulgaria 10

Predicate logic - definition

• Predicate logic uses a wholly unambiguous formal language interpreted by mathematical structures

• Predicate logic is extension of propositional logic with separate symbols for predicates, subjects, and quantifiers

• Its formulas contain variables which can be quantified• Predicate - a verb phrase template that describes a

property of objects, or a relationship among objects represented by the variables

• Quantification - two common quantifiers are the existential and universal quantifiers

Page 11: TENCompetence Workshop - Stimulating Personal Development and Knowledge SharingOctober, 30-31, 2008, Sofia, Bulgaria1 A formal approach to adaptive content

TENCompetence Workshop - Stimulating Personal Development and Knowledge Sharing October, 30-31, 2008, Sofia, Bulgaria 11

Learner Model - predicates

• user_learning_style(user_id,learning_style, value) as learning style={visual, auditory, kinesthetic}

• user_knows_subject(user_id, subject_id)• user_knows_domain(user_id, domain_id)• user_knows_learning_object(user_id, lo_id)• user_performance(user_id, subject_id, control_point_id,

value) as value={pass, fail, notReach}

Page 12: TENCompetence Workshop - Stimulating Personal Development and Knowledge SharingOctober, 30-31, 2008, Sofia, Bulgaria1 A formal approach to adaptive content

TENCompetence Workshop - Stimulating Personal Development and Knowledge Sharing October, 30-31, 2008, Sofia, Bulgaria 12

Domain Model - predicates

• domain_lo(domain_id, lo_id)• parent_lo(lo_parent_id, lo_child_id)• inheritor_lo(lo_main_id, lo_inheritor_id)• test_question_lo(lo_id, test_question_id)• test_answers(test_question_id, answer_id,

value)

Page 13: TENCompetence Workshop - Stimulating Personal Development and Knowledge SharingOctober, 30-31, 2008, Sofia, Bulgaria1 A formal approach to adaptive content

TENCompetence Workshop - Stimulating Personal Development and Knowledge Sharing October, 30-31, 2008, Sofia, Bulgaria 13

Adaptation Model - predicates

• lo_4_subject(subject_id, lo_id)• control_point_4_subject(subject_id,

control_point_id)• cp_path_4_graph(subject_id, path_id)• page_4_cp_path(path_id, page_id)• annotation_cp(learning_style, control_point_id,

value)• link_pages(current_page_id, next_page_id)• link_pages_annotation(learning_style, link_id,

annotation)

Page 14: TENCompetence Workshop - Stimulating Personal Development and Knowledge SharingOctober, 30-31, 2008, Sofia, Bulgaria1 A formal approach to adaptive content

TENCompetence Workshop - Stimulating Personal Development and Knowledge Sharing October, 30-31, 2008, Sofia, Bulgaria 14

Adaptation Engine - predicates

• next_cp_path(user_id, subject_id, previous_cp_id)

• sub_precondition(subject_new_id, subject_old_id)

• precondition_subject(subject_new_id) • user_precondition(user_id, subject_id)

Page 15: TENCompetence Workshop - Stimulating Personal Development and Knowledge SharingOctober, 30-31, 2008, Sofia, Bulgaria1 A formal approach to adaptive content

TENCompetence Workshop - Stimulating Personal Development and Knowledge Sharing October, 30-31, 2008, Sofia, Bulgaria 15

Adaptive rules - starting rules

• If the user knows all learning objects contained in a

domain/subject, then she/he knows that domain/subject – (1),(2)

• If the learner knows all subjects, which participate in precondition for given subject, then the learner can start learning it – (3), (4)

( _ ( , ) _( _ _ ( , ))_ _ ( , )

1) i j k j k i k

i j

user domain lo domain lo domain lo user knows learning object user louser knows domain user domain

( _ 4 _ ( , ) _ _(2) _ ( , ))_ _ ( , )

i j k j k i k

i j

user subject lo lo subject subject lo user knows learning object user louser knows subject user subject

( _ ( , )) _ _ ( , , )(4) i i j i juser user precondition user subject next cp path user subject null

( _ _ ( , ) _ ( ,( )) )_ ( )

3,

j i i j k j

i k

subject user user knows subject user subject sub precondition subject subjectuser precondition user subject

Page 16: TENCompetence Workshop - Stimulating Personal Development and Knowledge SharingOctober, 30-31, 2008, Sofia, Bulgaria1 A formal approach to adaptive content

TENCompetence Workshop - Stimulating Personal Development and Knowledge Sharing October, 30-31, 2008, Sofia, Bulgaria 16

Adaptive rules – pass-through graph rules

• If the learner passes or not control point’s test, she/he continues respectively forward (5) or backward (6):

( _ ( , , _ int , ))

_ _ ( , , _ i

(5

nt )

) i j k

i j k

k user performance user subject control po pass

next cp path user subject control po

1

( _ ( , , _ int , ))

_ _ ( ,

(6

, _ int )

) i j k

i j k

k user performance user subject control po fail

next cp path user subject control po

Page 17: TENCompetence Workshop - Stimulating Personal Development and Knowledge SharingOctober, 30-31, 2008, Sofia, Bulgaria1 A formal approach to adaptive content

TENCompetence Workshop - Stimulating Personal Development and Knowledge Sharing October, 30-31, 2008, Sofia, Bulgaria 17

Adaptive rules–updating LM rules

• If the learner passes all control point’s tests for particular subject then the learner knows this subject – (7)

• If the learner passes particular control point’s test then she/ he knows learning objects contained in the selected control point path – (8)

( _ ( , , _ in(7 t , ))_ _ ( , )

) i j k

i j

k user performance user subject control po passuser knows subject user subject

, , , , ( _ ( , , _ int , )_ 4 _ _

(8)( , ) _ 4 _ ( , ))

_ _ _ ( , )

i j l

m d d k

i k

k i j d l m user performance user subject control po passpage cp path path page lo page page louser knows learning object user lo

Page 18: TENCompetence Workshop - Stimulating Personal Development and Knowledge SharingOctober, 30-31, 2008, Sofia, Bulgaria1 A formal approach to adaptive content

TENCompetence Workshop - Stimulating Personal Development and Knowledge Sharing October, 30-31, 2008, Sofia, Bulgaria 18

Future works

• More precise formal model• Evaluate and compare our formal model with

others similar• Implement adaptation mechanism from our

formal model• Artificial intellect in adaptive engine

Page 19: TENCompetence Workshop - Stimulating Personal Development and Knowledge SharingOctober, 30-31, 2008, Sofia, Bulgaria1 A formal approach to adaptive content

TENCompetence Workshop - Stimulating Personal Development and Knowledge Sharing October, 30-31, 2008, Sofia, Bulgaria 19

Q & A

Thank you for your attention

Email : [email protected]

Skype : ddessy