Keppel Ltd. 1Q 2024 Business Update Presentation Slides
Adpative learning environment diffusable
1. Adaptive Learning
Environment
Mona LAROUSSI
"The best way to predict the
future is to invent it."
Alan Kay 1
2. Summary
y
• The need for adaptation
– personalized: adaptable / adaptive /
T flexible etc
B
• L
Learner M d li
Modeling
• Different kind of Adaptation
p
– adaptive presentation
– adaptive navigation
– Adaptive interaction
• Our work
"The best way to predict the
future is to invent it."
Alan Kay 2
3. We live in a “one size fits all” world
one all
"The best way to predict the
future is to invent it."
Alan Kay 3
4. But we are not all the same size
"The best way to predict the
future is to invent it."
Alan Kay 4
5. Automatic ≠ Adaptive
Fixed behavior automatic behavior that
depends on
environmental factors
"The best way to predict the
future is to invent it."
Alan Kay 5
6. Adaptation in any type of
Information System
• Ad t ti of the Information
Adaptation f th I f ti
– information adapted to who/where/when you are
– information adapted to what you are doing and what
you have done before (e.g. learning)
– presentation adapted to circumstances (e.g. the
device you use, the network, etc.)
• Adaptation of the Process
– adaptation of interaction and/or dialog
– adaptation of navigation structures
– adaptation of the order of tasks and steps
"The best way to predict the
future is to invent it."
Alan Kay 6
7. Disadvantages of Adaptive Systems
• may l
learn th wrong b h i
the behavior
• Adaptive Systems may outsmart the users
"The best way to predict the
future is to invent it."
Alan Kay 7
8. Advantages of Adaptive Systems
• Increased efficiency:
I d ffi i
• Return on investment
"The best way to predict the
future is to invent it."
Alan Kay 8
9. Main issues in Adaptive Systems
• Questions to ask when designing an adaptive application:
– Why do we want adaptation?
– What can be adapted?
– What can we adapt to?
– How can we collect the right information?
– How can we process/use that information
"The best way to predict the
future is to invent it."
Alan Kay 9
16. Learner Profile
• Common term for user models
• This information is used to get the user to more
g
relevant information
• Views on user profiles in IR community
– Classic - a reference point
– Modern - simple form of a user model
"The best way to predict the
future is to invent it."
Alan Kay 16
17. Core vs. Extended User Profile
vs
• C
Core profile
fil
– contains information related to the user
search goals and interests
• Extended profile
p
– contains information related to the user as a
p
person in order to understand or model the
use that a person will make with the
information retrieved
"The best way to predict the
future is to invent it."
Alan Kay 17
18. Group Profiles
• A system can maintain a group profile i
t i t i fil in
parallel or instead of user profile
• Could resolve the privacy issue
(navigation with group profile)
• Could be use for new group members at
the b i i
h beginning
• Could be used in addition to the user
profile to add group “wisdom”
"The best way to predict the
future is to invent it."
Alan Kay 18
19. Extended Profile
• Goals
G l
• Interests
• Background:
• Preferences
• Learning styles
"The best way to predict the
future is to invent it."
Alan Kay 19
20. Who Maintains the Profile?
• Profile is provided and maintained by
the user/administrator
– Sometimes the only choice
• The system constructs and updates the
profile ( t
fil (automatic personalization)
ti li ti )
• Collaborative - user and system
y
– User creates, system maintains
– User can influence and edit
– Does it help or not?
"The best way to predict the
future is to invent it."
Alan Kay 20
23. Learning Management Systems
• LMSs offer a “personal” learning
environment:
– registration for courses
– personalization of the “workspace”
workspace
– access to course material
– assignments, tests, group work
– communication tools: messages, discussion
g ,
forums, chat
– no built-in adaptive learning functionality
built in
"The best way to predict the
future is to invent it."
Alan Kay 23
24. Evaluation of adaptativity in LMS by QWS method
Adaptabilité Personnalisation Extensibilité Adaptativité Rang
Valeur maximum * # * *
ATutor | # # | 3
Dokeos | 0 * + 2
dotLRN + + * 0 2
ILIAS + # * 0 2
LON‐CAPA
LON CAPA + # # | 2
Moodle # + * | 1
OpenUSS # # # 0 2
Sakai 0 0 * 0 3
Spaghettilearning + # + 0 3
"The best way to predict the
future is to invent it."
Alan Kay 24
25. What can we Adapt to?
• Knowledge of the user
g
– initialization using stereotypes (beginner, intermediate, expert)
– represented in an overlay model of the concept structure of the
application
– fine grained or coarse grained
– based on browsing and on tests
• Goals, tasks or interest
– mapped onto the applications concept structure
– difficult to determine unless it is preset by the user or a workflow
system
– goals may change often and more radically than knowledge
"The best way to predict the
future is to invent it."
Alan Kay 25
26. What can we Adapt to? (cont )
(cont.)
• B k
Background and experience
d d i
– background = user’s experience outside the application
– experience = user’s experience with the application’s
user s application s
hyperspace
• Preferences
– any explicitly entered aspect of the user that can b used f
li i l d f h h be d for
adaptation
– examples: media preferences, cognitive style, etc.
• Context / environment
– aspects of the user’s environment, like browsing device,
window size network bandwidth processing power etc
size, bandwidth, power, etc.
"The best way to predict the
future is to invent it."
Alan Kay 26
27. What Do We Adapt in ALE?
• Ad ti presentation:
Adaptive t ti
– adapting the information
– adapting the presentation of that information
– selecting the media and media-related factors such
as image or video quality and size
• Adaptive navigation:
– adapting the link anchors that are shown
– adapting the link destinations
– giving “overviews” for navigation support and for
overviews
orientation support
"The best way to predict the
future is to invent it."
Alan Kay 27
28. What Do We Adapt in ALE?
• Ad ti i t
Adaptive interaction:
ti
– Answer
– question
– Nature
• Adaptive communication:
– Tools
– Use of tools
"The best way to predict the
future is to invent it."
Alan Kay 28
29. "The best way to predict the
future is to invent it."
Alan Kay 29
30. Content Adaptation
• Inserting/removing fragments
– prerequisite explanations: inserted when the user appears to
need them
– additional explanations: additional details or examples for some
dditi l l ti dditi l d t il l f
users
– comparative explanations: only shown to users who can make
the comparison
• Altering fragments
– Most useful for selecting among a number of alternatives
– Can be done to choose explanations or examples, but also to
choose a single term
• Sorting fragments
g g
– Can be done to perform relevance ranking for instance
"The best way to predict the
future is to invent it."
Alan Kay 30
31. Content adaptation
• St t ht t
Stretchtext
• Dimming fragments
"The best way to predict the
future is to invent it."
Alan Kay 31
32. Adaptive Navigation Support
• Direct guidance
g
• Adaptive link
• Variant: Adaptive link destinations
p
• Adaptive link annotation
• Adaptive link hiding
dap e d g
"The best way to predict the
future is to invent it."
Alan Kay 32
33. Connexion à
la plateforme Sélection du style
d’apprentissage & des
Mise à jour du
style et des
préférences de
préférences Étudiant l’étudiant
associés à
l’étudiant
Auditif Visuel Kinesthésique
Observation de
l’utilisation de la
l’utilisation de la
plateforme
Actions adaptatives
Plateforme Plateforme Plateforme
Adapté au style Adapté au style Adapté au style
Auditif Visuel kinesthésique
"The best way to predict the
future is to invent it."
Alan Kay
34. Our work
"The best way to predict the
future is to invent it."
Alan Kay 34
37. L’apprentissage malléable :
Concepts de base
Activité
Apprenant
• Inspiré de la théorie de
l activité d études
l’activité : théorie d’études
socioculturelles
Environnement
Contexte
d’interaction
"The best way to predict the
future is to invent it."
Alan Kay 37
38. Le méta-modèle du langage
class Class M d
o el
CAAML
S artO
m bject E b d
m ed edE v
n iron entalSens r
m o
ContextAdaptativityCondition Organisation Manifest
Activity daptativity ondition
A C Sensor
M bileD iceSens
o ev or
1..* 0..*
LearningDesign
C d p
oA aptativityC dition
y on Tool M bileD
o evice
1..* 1..* 0..*
Prereq ites
uis
Global Caracteristics
0..* 0..*
* Ressource
Service
Condition LearningScenario M bile
o
*
uses Software
Dynamic Objectives Pervas e
iv
1..*
Context LearningR ource
es P y ic
h s al
Phase
*
ELearning
*
Static 1..*
Person Learn g
in C hin
oac g
* RolePart
*
+using
Role +performs
Activity Activity ontext
C
*
"The best way to predict the A ti it S
ctivityStruc re
t tut
+creates *
future is to invent it."
Alan Kay
+triggers 38
Notification Outcome
39. Le projet ContAct-Me
Contact‐Me qui est un environnement auteur
Contact Me qui est un environnement auteur
dédié à l’apprentissage malléable basé sur le
langage CAAML . Et se compose de deux modules
l C d d d l
de base:
Le modeleur (modélisation et transformation de
Le modeleur (modélisation et transformation de
modèles) ‐ en design time
Le générateur d applications d apprentissage
Le générateur d’applications d’apprentissage
malléable et simulateur de l’exécution des
activités contextualisées et adaptatives en run
i ié li é
"The best way to predict the
future is to invent it."
d i
Alan Kay 39
time
40. ContAct-Me
A c tiv i té A c t iv i t é d e
d 'a p p r e n t i s s a g e c o a c h in g
S u p p o rt m o b il e
S c é n a r io A c t iv it é
id : i n t e g e r 1 .. * 1 . .*
o u t i l m é th o d o l o g iq u e id :i in te g e r
O u t il p h y s iq u e in t i t u lé : s t r in g n o m :in t e g e r
d e s c r ip t i o n : s t r in g 1 . .* D e s c r i p t io n : s tr i n g
Module de S u je t
1 ..* 1 . .*
O u til O b je t
0 ..*
R e la t io n
1 ..*
R e la t io n - t y p e
1 ..*
id :
1 ..* 1 .. *
1
C o n te x t
in te g e r
1 ..*
R o le
E le m e n t c o n t e x t u e l
a c tiv i té
1 .. *
E le m e n t c o n te x tu e l
Le langage CAAML
Transformatio
E l é m e n t c o n te x tu e l
a p p re n a n t
n o m : s t r in g
d e s c r ip ti o n : s t r in g
1 . .*
R è g le
0 .. * 0 ..* E l e m e n t c o n te x tu e l
s t a tiq u e
G r o u p e
n b r e -m e m b r e : in t e g e r
R è g le d 'i n f é r e n c e 0 ..1
n CAAML
1 . .* E lé m e n t c o n te x tu e l
W e b S e r v ic e d y n a m iq u e
p a t h : s trin g s e u i _ t o lé r a n c e _ m i n : s t r i n g
s e u i _ t o lé r a n c e _ m a x : s t r i n g
S o u rc e d 'a c q u is i tio n a d a p t a t if : b o o le a n
1 ..* V a le u r : s t r in g
C a p t e u r
Id : s t rin g 0 ..*
ty p e : T y p e -c a p te u r D e s c r ip t io n : s tr in g
/IMS LD
/IMS-LD Méta modèle d activités
Méta‐modèle d’activités
contextualisées et des
(ATL) règles de co‐adaptativité
Module de
réutilisation
Modèle Modeleur graphique
des modèles
CAAML
Modèle IMS‐LD IMS-LD
IMS LD (sans (GMF,
(GMF GEF et RCP)
mobilité)
Module de
transformation
CAAML EN
modèle IMS-LD
IMS LD
étendu
Modèle CAAML
Génération
Générateur d’applications
d applications
et
émulation d’apprentissage malléable à
d’interfaces partir de modèles
mobiles en
XHTML MP
XHTML-MP
(XSLT, Un Simulateur de l’exécution
Modèle IMS‐LD étendu
(XML) XHTML-MP) de la co-adaptativité entre
contexte et application Simulation de
(DIASIM) l’exécution de
la co-
"The best way to predict the adaptativité
future is to invent it." entre contexte
Alan Kay et activités
42. Interrogation du profil LIP suivant un
langage de requêtes graphique offrant des
langage de requêtes graphique offrant des
fourchettes (date, activités, par un ou
groupe d’apprenants)
"The best way to predict the
future is to invent it."
Alan Kay 42
42
43. Fractal adaptive ws
User model’s adaptation
Adaptation layer
Context’s adaptation
Mobility layer Mobility layer An adaptive
Composition
Web service Web service
Web service
Mobile adaptive
Web service
Mobile Web
service
An adaptive composite Web service
"The best way to predict the
future is to invent it."
Alan Kay 43
44. Adaptive scos
SCO11
SA2
SCO1.htm
SCO1 ht SCO12 ? Apprenant
2
SCO13
SA3
Ressources Apprenant
alternatives 3
Manifest Ressource SCO11
SA1
s SCO12
Cours SCO13
Activité1 SCO1.htm Apprenant
1
Activité2 SCO2.doc SCO21
Activité3 SCO3.pdf SCO22
SCO31
"The best way to predict the SCO32
future is to invent it." SCO33
Alan Kay 44
SCO34
45. And …..
"The best way to predict the
future is to invent it."
Alan Kay 45
46. 4 YOUR
OU
"The best way to predict the
future is to invent it."
Alan Kay 46