Upload
others
View
2
Download
0
Embed Size (px)
Citation preview
1
Distributed and United
J.Vassileva ICCE'2001 Invited Talk 1
Julita VassilevaComputer Science DepartmentUniversity of SaskatchewanSaskatoon, Canada
This talk is dedicated to my 9th grade math teacher
E il P
J.Vassileva ICCE'2001 Invited Talk 2
Emil Popov
ContentsIndividualization Learning communitiesI-HelpTh i f ti ti ti i ti
J.Vassileva ICCE'2001 Invited Talk 3
The issue of motivating participationThrough compassionThrough moneyThrough friends
Creating a culture
What makes a good teacher?
Mastery of materialAbility to organize the presentation and interaction with the learner
J.Vassileva ICCE'2001 Invited Talk 4
te act o t t e ea ePedagogical skillsUnderstanding the learner
These features have been addressedby research in AI and Education
2
What makes a great teacher?
Ability to guide “discovery”, leadershipAbility to motivate and pushSpontaneity and surprise
J.Vassileva ICCE'2001 Invited Talk 5
Spontaneity and surprisePersonality and artistic skillCharisma …
We have tried to simulate the teacher
CAI in the 60’sMultimedia courseware continues to be “b t ll ” i th 90’
J.Vassileva ICCE'2001 Invited Talk 6
“best-seller” in the 90’sWeb-based courses – big and growing market now
Pedagogically – not too successful
Focus on the individual
Dynamic Courseware Generation (DCG)Reactive Planning of:
Contents
J.Vassileva ICCE'2001 Invited Talk 7
ContentsPresentation strategyProblem-solving (coaching)
Overlay Student Modelling
Dynamic Course Generation (DCG)(Vassileva, 1992, 1994, 1997)
Course
Plan
J.Vassileva ICCE'2001 Invited Talk 8
Course
Student Model
0.850.3
0.9
3
Pedagogical Planning in DCG
Give Example Test KnowlePresent the goalShow task planIntrod uceExplainProble m Give Ex ercise
J.Vassileva ICCE'2001 Invited Talk 9
Ma ke ExercisePresentExercise VerifyChec kRespo nseInform Student RemedyE xplainGive Correct SolutiElaborate onsub-problemby description by analogy
Make ExercisePresentExerciseVerifyCheckResponseInform StudentRemedyExplainGive Correct SolutionElaborate onsub-problemsRetryGiveHintby descriptionby analogyGive ExampleTest KnowledgePresent the goalShow task planIntroduceExplainGive provoking ProblemGive ExerciseTeach concept
Coaching Users in Problem Solving
∫ + 221
xdx
∫ + 221
xdx∫ − 22
1xdx
Partial Fractions+
Substitution∫ − 42
221
x
dx
Variable under Differential
J.Vassileva ICCE'2001 Invited Talk 10
∫ + 22 x2
duuu
∫ −421
2ln21
−x 2ln21
+x4ln
21
−u
4ln21 2 −x
Substitution u=x2
Reverse Substitution
Algebraic Transformation
Adaptive Teaching: Planning contents and delivery
Planning
System
DCG:
J.Vassileva ICCE'2001 Invited Talk 11
Problem Solving
System teachingPlanning
contents
Planning delivery
User doing things
Initi
ativ
e
User
I too want individualized instruction!
The ultimate result?Instruction ultimately tailored to the individual A system that truly “cares” for the learner
J.Vassileva ICCE'2001 Invited Talk 12
But maybe sometimes the learner should adapt, not the environment?Otherwise it would be a very lonely learner
4
Learning is adapting
Dialectic between Cognition and Experience (Immanuel Kant, 1781).
Cognition**
J.Vassileva ICCE'2001 Invited Talk 13
Cognition
Experience**Experience***
Experience****
Cognition* Cognition***
Cognition*
erience*
Experience*Maturana & Varella
Learning is communication
Conversation Theory of Cognition (Pask, 1973)
J.Vassileva ICCE'2001 Invited Talk 14
Representation* Representation^
Representation** Representation^^
Representation^^^Representation***
Focus on the learning experience and communication
In the last 10 years we have seen:ConstructivismSocial cognition
J.Vassileva ICCE'2001 Invited Talk 15
Social cognitionCollaborative learning environmentsOpen learning environments
Technology development
• distributed applications: plug-ins, applets, shared object libraries
connected users resources applications
Distributed Environments
J.Vassileva ICCE'2001 Invited Talk 16
• connected users, resources, applications• hybrid societies
5
Learning communitiesHow to provide continuous support for a community of learners?How to provide a shared medium?
J.Vassileva ICCE'2001 Invited Talk 17
How to cater to the individual ? How to motivate participation?How to ensure focus and guidance?
These are some of the features that make the great teacher!
Large classesNo possibility for individualized
J.Vassileva ICCE'2001 Invited Talk 18
p yfeedbackVarious levels of knowledge in the class
Students could help each other!(Jim’s and Gord’s idea)
I-Help: a community of peersBecause..
…
J.Vassileva ICCE'2001 Invited Talk 19
?But..
What is the shared medium?
Public discussion forum (asynchronous)E-mail (asynchronous)
J.Vassileva ICCE'2001 Invited Talk 20
( y )2-line chat tool (synchronous) Chat-rooms (synchronous)
6
Individualization in I-Help
In matching people with appropriate partners depending on their
Knowledge l
Modelling user’s knowledge
aker
s From self-evaluationFrom diagnostic applicationsF di ti li ti
J.Vassileva ICCE'2001 Invited Talk 21
Cognitive styleStar-signEagernessHelpfulnessSocial rankingRelationships
Modelling other individual characteristics
Modelling social characteristics of users in the context of the communityD
iffer
ent
Mat
chm
a From diagnostic applicationsFrom peer-helper evaluationFrom diagnostic application
From diagnostic applicationFrom peer-evaluation
From diagnostic applicationFrom self-evaluationFrom agent-evaluation
From self-evaluation
Distributed learner modelling “Active”
No predefined behavior to be adapted Behavior Emerges !
“Just in time” generated models D di
Vassileva J., McCalla G.,Greer J., (to appear) Distributed UserModelling,in User Modelling andUser AdaptedInteraction
J.Vassileva ICCE'2001 Invited Talk 22
Depending on:The purpose of adaptationThe available user model informationThe trust relationships with other agentsThe circumstances (who is around) and resources
Focus on the process, not representation
Interaction, Special issue on Intelligent Agents.
I-Help deployment results
Deployed for 2 years, 2000+ users, all undergrad CS classes, in the UK, France and Colombia
Lessons learned:
Greer J., McCalla G., Vassileva J., Deters R., Bull S., Kettel L. (2001)
J.Vassileva ICCE'2001 Invited Talk 23
Lessons learned: Usage / participation varies greatlyShould be perceived as adding value
Initial knowledge investment from instructor is crucial (apprenticeship)After reaching a “critical mass” becomes self-feeding
Kettel L. (2001) Lessons Learned in Deploying a Multi-Agent Learning Support System, ProceedingsAIED'2001,410-421.
The most important lesson
The most exiting technology is worthless, if not embraced by a large user community
J.Vassileva ICCE'2001 Invited Talk 24
Example: NAPSTER, KaZaA
A very simple technology can be invaluable, if supported by an active user community
7
How to motivate participation?
Why do people offer their time and resources? Different people have different motivationsSome are altruists (intrinsically motivated)S ld h l th i f i d d h t k
…
J.Vassileva ICCE'2001 Invited Talk 25
Some would help their friends and hope to make new friends through helping Some seek glorySome seek attentionSome seek high marks Some seek money…
(extrinsically motivated)
Friends Forever
We need to provide a mechanism that appeals toevery individual, depending on his/her motivation
Animated, believable interface Agents Personal agent as a personaGoal:
Appealing to the compassionate
J.Vassileva ICCE'2001 Invited Talk 26
Goal: to invoke emotion (compassion) in the userto persuade user to help
Study: the persuasive power of an “emotional” agent
Experiment with EmotionGoal: to find if integrating emotional qualities into personasimpacts the student’s performance and perception of learning
• Experiment:An introductory interactive course on C++ delivered by an animated persona
J.Vassileva ICCE'2001 Invited Talk 27
- material presented by human voice
- users have to answer test questions
- persona responds to test performance with facial expression
• Two test conditions:- Emotional engine = “on”- Emotional engine = “off”
Emotional Engine in the PersonaValenced Reaction To
Consequences of Events (Pleased,
Actions of Agents (Approving,
Disapproving etc.)
Aspects of Objects (Liking,
J.Vassileva ICCE'2001 Invited Talk 28
Displeased etc.) disliking etc.)
Emotion States
Happy Sad Pleased Surprised Neutral Angry
Facial expression for six major emotional states (Ortony,1988)
8
Preliminary Results
Girls felt a pressure to perform better in order to please the persona!all participants preferred the
Okonkwo, C., Vassileva, J. (2001) Affective Pedagogical Agents and User Persuasion, C. Stephanidis (ed.) Proc. "Universal Access in Human-Computer Interaction (UAHCI)", HCI International,New Orleans 397-401
J.Vassileva ICCE'2001 Invited Talk 29
• all participants preferred the emotional persona
• no significant difference in the student’s performance
New Orleans,397 401.
Appealing to the materialistic
J.Vassileva ICCE'2001 Invited Talk 30
Human help has costs (time, effort)! It shouldn’t be misused!
The I-Help economy
Market regulates the supply and demand
J.Vassileva ICCE'2001 Invited Talk 31
help in exchange for currencyrate of pay negotiable (by agents)users can set parameters of agentspay a penalty if agent’s deals are ignored
The agent negotiation
Each agent decides to counter-offer or accept an offer by calculating a utility function with factors:
i t ( di ti i f )
C. Mudgal, J. Vassileva (2000) Multi-agent negotiation to support an economy for online help andtutoring, Proceedings of ITS'2000, Springer LNCS 1839, 83-92.
J.Vassileva ICCE'2001 Invited Talk 32
money importance (greediness, stinginess of user)importance of the current goalimportance of the relationship between the usersrisk attitudeperceived utility function and factors of the other agent agents model each other
9
The currency
A bit like Sun java’s “Duke Dollars”Everyone gets an initial allotment
helpees pay, helpers earn
J.Vassileva ICCE'2001 Invited Talk 33
helpees pay, helpers earnwhat happens when someone runs out?finding useful course resources pays
Redeemable for “prizes”
How to cash in the end?Depends on the values of the community
Marks – in a real classroom settingReal money – in a workplace setting /distance educReputation (top 10 list) – always useful
J.Vassileva ICCE'2001 Invited Talk 34
Visibility in the society based on reputation –Slashdot.com, thewines.com
In our caseMarks – not allowedSouvenirs not stimulatingReputation, visibility – a better way
…
How to steer the economy?
Resources
Pull money out by rewardingstudent with marks / items
$$$
Free instructional resources
$
$$
“Big Brother”
Agent market economy
Allowance or “salary”
“Taxation”Simulations:• Electronic marketplaces• Agent society, emerging norms• Emerging groups • Emerging cooperation among agents
Ethi l thi l t
J.Vassileva ICCE'2001 Invited Talk 35
Users
$
Users
Agent market economy
Real world help market
Real world evaluations:• Real rewards• Monitoring user activity• Comparing with agent models• Reconstructing scenarios• Questionnaires
• Ethical vs. non-ethical agents• Looking for equilibrium states• What measures effect the emerging behaviour and equilibriums
social systems simulation
Friends Forever
Supporting social relationships
Agents can take into account interpersonal relationships
In seeking helpIn negotiation
Breban S., Vassileva J.(2001)
J.Vassileva ICCE'2001 Invited Talk 36
In negotiationAgents can help in building new relationships among users
Agent coalition formationTrust-based mechanism
Forming user groups
(2001)Long-Term Coalitions for the ElectronicMarketplace,Proc.E-commerceWorkshop,Canadian AIConference, Ottawa.
10
Simulation results
In the agent world, simulation shows that coalition formation brings
stability, predictability in the agent societyi d b fit f th t
J.Vassileva ICCE'2001 Invited Talk 37
increased benefits for the agents
In the human world, still to evaluate Can people become friends through their agents?Does agent coalition help build stable and productive learner teams?
Create a learning culture!
The 5 “R”s (Hilarie Davis): Roles – people who sustain the communityRules – ethics of behaviour, reward system
J.Vassileva ICCE'2001 Invited Talk 38
Rituals – routines, predictable things, to make the participants feel safeRounds – regular events, customs, things to expect and look forward toRings – surprises, interesting unexpected things, “be always there or you’ll miss it!”
How to ensure focus and guidance?
Rituals – How to make users feel safe:“Anonymous” usersOne user different rolesBut then how do you find your
?
J.Vassileva ICCE'2001 Invited Talk 39
But then how do you find yournew I-Help friend in the real classroom?
How to plan surprise?
How to make them come back again?
Conclusions
Ultimate Individualization Distributed, Lonely Learners
J.Vassileva ICCE'2001 Invited Talk 40
Learning Communities United Learners
11
ConclusionsSupporting Learner Communities
Multi-Agent Architectures provide a lot of useful tools and metaphorsIndividualization is important
J.Vassileva ICCE'2001 Invited Talk 41
Motivation is important (individualization here too!)Research into heterogeneous agent economiesis needed (differently motivated agents)Studying the culture of the user population and creating a productive learning culture is vital!
Questions?
More Information: http://julita.usask.ca/http://bistrica usask ca/madmuc/
J.Vassileva ICCE'2001 Invited Talk 42
http://bistrica.usask.ca/madmuc/http://www.cs.usask.ca/projects/aries
Contact: [email protected]