Using Ontological Engineering to Support the Development of - - PowerPoint PPT Presentation

SLIDE 1

Using Ontological Engineering to Support the Development of Theory-aware Collaborative Learning Applications

Seiji Isotani

isotani@acm.org

Riichiro Mizoguchi

mizoguchi@ei.sanken.osaka-u.ac.jp

The Institute of Scientific and Industrial Research Osaka University, Japan

(advisor)

SIGCSE – Student Research Competition

SLIDE 2

• 1. The Challenges: Group Formation and CSCL Design and Analysis
• 2. Approach
• Typical Approach
• Ontological Approach
• Main Goals
• 3. GMIP – Growth Model Improved by Interaction Patterns
• Ontological Structure to Describe Learning Theories
• Benefits
• Applications
• 4. Overview of CSCL Research Area
• 5. Conclusions

Agenda

SLIDE 3

Group

Teacher/Instructor How to design the best learning activities? Which Theory? What kind of benefits? How to analyze?

learning by

• bservation

learning by guiding learning by apprenticeship Learner A Learner B Learner C

Learner Supported theory Learning strategy Role for learner Proposed activities desired Benefit Master Guide learner B Imitate learner A Observe the interactions between A and B Apprentice Skill development Skill development Observer Knowledge acquisition Learner A Cognitive apprenticeship Learning by guiding Learner B Cognitive apprenticeship Learning by apprenticeship Learner C Observational learning Learning by

• bservation

Selection of an appropriate set of learning theories

Cognitive Apprenticeship Theory Observational Learning Theory

The Problems: Collaborative Learning Design and Analysis

Apprentice role Master role Observer role

SLIDE 4

Learning theories hard to understand too complex & ambiguous There is not a common vocabulary to describe them Different point of views, levels of aggregation, perspective and emphasis How to “unfold” the theories into a set of activities for a group? How to develop programs to support effective group formation and to design and to analyze group activities based on an well-grounded theoretical knowledge?

The Problem

SLIDE 5

Typical Approach and Limitations: Example

Soh, L., et al. Multiagent Coalition Formation for Computer-Supported Cooperative

• Learning. In Proceedings of IAAI, 2006, 1844-1851.

Jigsaw method learners

Group of 3 learners Group 1 Group 2 Group 3

Highest score Lowest score

evaluation

leader leader leader L1 L2 L3 L1 L2 L3

SLIDE 6

I-goal

Behavior

I-role You-role I-goal (I) Y<=I-goal

Behavior

W(A)-goal

Role

Y⇐I-goal

Role

Y⇐I-goal

W(L)-goal

Common goal Primary focus (P) Secondary focus (S) S<=P-goal P<=S-goal I-goal

Behavior

I-role You-role I-goal (I) Y<=I-goal

Behavior k./cog. state

Goal state I-goal

W(L)-goal k./cog. state (Group)

Goal state

How does the lea rner change his/her state? What activity does the group want to do? How does the group change its state?

G G G G

W hy does the learne r want to interact with other lea rners?

S S G

I-goal

Behavior

I-role You-role I-goal (I) Y<=I-goal

Behavior

I-goal I-goal I-goal I-goal

Behavior

I-role You-role I-goal (I) Y<=I-goal Y<=I-goal

Behavior

W(A)-goal

Role

Y⇐I-goal

Role

Y⇐I-goal

W(L)-goal

Common goal Primary focus (P) Secondary focus (S) S<=P-goal P<=S-goal W(A)-goal W(A)-goal

Role Role Role

Y⇐I-goal Y⇐I-goal Y⇐I-goal Y⇐I-goal

Role Role Role

Y⇐I-goal Y⇐I-goal Y⇐I-goal Y⇐I-goal

W(L)-goal

Common goal Primary focus (P) Secondary focus (S) S<=P-goal P<=S-goal I-goal

Behavior

I-role You-role I-goal (I) Y<=I-goal

Behavior

I-goal I-goal I-goal I-goal

Behavior

I-role You-role I-goal (I) Y<=I-goal Y<=I-goal

Behavior k./cog. state k./cog. state

Goal state I-goal I-goal I-goal

W(L)-goal k./cog. state (Group)

Goal state

How does the lea rner change his/her state? What activity does the group want to do? How does the group change its state?

G G G G

W hy does the learne r want to interact with other lea rners?

S S G

learning theories

Use ontological engineering to describe theories for CSCL Ontological structure Use ontologies to support the development of

• ntology-aware systems

users

teacher/instructor/designer

The systems help users to: propose group formation; design group activities; estimate benefits, etc..

Our Approach

SLIDE 7

Overview of CSCL Research Area

Technologies for Collaboration Technologies for Collaboration Methodologies to support CL process Methodologies to support CL process Pedagogical Approaches Pedagogical Approaches Learning Theories for CL Learning Theories for CL Group Formation for CL Group Formation for CL Foundations of Collaborative Learning (CL) Foundations of Collaborative Learning (CL) Interaction Analysis and Evaluation Methods Interaction Analysis and Evaluation Methods

Dillenbourg, P. Swiss Federal

• Inst. of Tech. Lausanne

Koschmann, T. Southern Illinois Univ.

Collaborative Learning Scripts Collaborative Learning Scripts

European CSCL Community American CSCL Community

Theoretical Frameworks and models Theoretical Frameworks and models

SLIDE 8

Fundamental settings for an effective CL session Essential conditions to predict the impact of interaction in the learning process Group Formation for CL Group Formation for CL Collaborative Learning Design Collaborative Learning Design Theoretical Frameworks and models Theoretical Frameworks and models Interaction Analysis and Evaluation Methods Interaction Analysis and Evaluation Methods Learning Theories for CL Learning Theories for CL

Ontologies

I-goal Behavior I-role You-role I-goal (I) Y<=I-goal Behavior W(A)-goal Role Y⇐I-goal Role Y⇐I-goal W(L)-goal Common goal Primary focus (P) Secondary focus (S) S<=P-goal P<=S-goal I-goal Behavior I-role You-role I-goal (I) Y<=I-goal Behavior k./cog. state Goal state I-goal W(L)-goal k./cog. state (Group) Goal state How does the lea rner change his/her state? What activity does the group want to do? How does the group change its state? G G G G Why does the learne r want to interact with othe r lea rners? S S G I-goal Behavior I-role You-role I-goal (I) Y<=I-goal Behavior I-goal I-goal I-goal I-goal Behavior I-role You-role I-goal (I) Y<=I-goal Y<=I-goal Behavior W(A)-goal Role Y⇐I-goal Role Y⇐I-goal W(L)-goal Common goal Primary focus (P) Secondary focus (S) S<=P-goal P<=S-goal W(A)-goal W(A)-goal Role Role Role Y⇐I-goal Y⇐I-goal Y⇐I-goal Y⇐I-goal Role Role Role Y⇐I-goal Y⇐I-goal Y⇐I-goal Y⇐I-goal W(L)-goal Common goal Primary focus (P) Secondary focus (S) S<=P-goal P<=S-goal I-goal Behavior I-role You-role I-goal (I) Y<=I-goal Behavior I-goal I-goal I-goal I-goal Behavior I-role You-role I-goal (I) Y<=I-goal Y<=I-goal Behavior k./cog. state k./cog. state Goal state I-goal I-goal I-goal W(L)-goal k./cog. state (Group) Goal state How does the lea rner change his/her state? What activity does the group want to do? How does the group change its state? G G G G Why does the learne r want to interact with othe r lea rners? S S G

CL Models

SLIDE 9

The Main Contribution of this Research

• 1. Making tacit characteristics of learning theories explicit;
• 2. Identifying the relationships among interaction, learning

strategies and learning goals;

• 3. To propose an ontological structure to describe learning

theories and to extend the Collaborative Learning Ontology [Inaba et al, 2000].

• 4. To support effective group formation, the design of CL

activities and the analysis of learner’s interactions.

“We are NOT trying to coalesce several learning theories into a single ontology”

SLIDE 10

Collaborative Learning Ontology [inaba et al, 2000]

LA LC

I-goal(LB) I-goal(LA) Y<=I-goal (LB<=LA) Y<=I -goal(LA<=LB)

LB

Learning Strategies Learning Goals

Interaction Patterns

HOW?

SLIDE 11

LA

I-goal(LB) I-goal(LA)

Y<=I -goal(LA<=LB) Interaction

Instructor Event Learner Event Influential I_L Events

Interaction Patterns for Learning Theories proposed by Inaba et al. 2003 Interaction Patterns for Learning Theories proposed by Inaba et al. 2003 Anchored Instruction Anchored Instruction Peer Tutoring Peer Tutoring Distributed Cognition Distributed Cognition LPP LPP Cognitive Constructivism Cognitive Constructivism Cognitive Flexibility Theory Cognitive Flexibility Theory Sociocultural Theory Sociocultural Theory Observational Learning Observational Learning Cognitive Apprenticeship Cognitive Apprenticeship

Analyzing and Remodeling Interaction Patterns

Interaction 3 Interaction 2 Interaction Interaction 4

Pattern

Y<=I -goal(LB<=LA)

Learning Theory

Action Action

Necessary Interaction Desired Interaction

Role Role

LB

SLIDE 12

Ontological Structure to Describe a Learning Theory

Instructional event Influential I_L event

I event

I-goal

Instructor Benefits for the Instructor

Agent Action

Instructional action L event Learner

Agent Action

Learning action

Learning event I-goal

Benefits for the Learner Interaction Pattern

Y<=I-goal Learning Theory

Teaching-Learning Process Learning Strategy

I-goal

I-role I-goal

Agent Agent

You-role

G

Necessary Interaction Activity

* *

Influential I_L event

Desired Interaction Activity

Influential I_L event

* *

SLIDE 13

Example: Cognitive Apprenticeship Theory

Instructor Event

SLIDE 14

Cognitive Apprenticeship

3: Clarifying the problem* 4: Monitoring 5: Notifying how the learner is 9: Affirmative reaction 2: Demonstration how to solve a problem 8: Showing a solution 1:Setting up learning context 6: Instigating Thinking 7: Requesting problem's details

Interaction Pattern represented by Influential I_L Events LGM – Learner’s Growth Model [extend from Inaba et al, 03]: it shows the learner’s knowledge acquisition process [Rumelhart & Norman,78] and skill development process [Anderson, 82].

SLIDE 15

S(0,0) S(0,1) S(0,2) S(0,3) S(2,0) S(1,0) S(3,0) S(4,0) S(1,1) S(2,1) S(3,1) S(4,1) S(1,2) S(2,2) S(3,2) S(4,2) S(1,3) S(3,3) S(2,3) S(4,3)

Cognitive Apprenticeship

Learning by Apprenticeship

[Stages of Skill development] nothing (0) rough cognitive stage (1) explanatory cognitive stage (2) associative stage (3) autonomous stage (4) [Stages of Knowledge acquisition] nothing (0) tuning (2) restructuring (3) accretion (1)

GMIP - Growth Model Improved by Interaction Patterns

SLIDE 16

S(0,0) S(0,1) S(0,2) S(0,3) S(2,0) S(1,0) S(3,0) S(4,0) S(1,1) S(2,1) S(3,1) S(4,1) S(1,2) S(2,2) S(3,2) S(4,2) S(1,3) S(3,3) S(2,3) S(4,3)

Cognitive Apprenticeship

Learning by Apprenticeship

x y Complementary Interaction Necessary Interaction The dashed ellipses means that the interaction on the top/left must be followed by another interaction bottom/right. The ellipses means that the interaction on the top/left will be followed by another interaction bottom/right and vice-versa (cycle) . 4 5 6 9 7 8 2 1 2 3 2 4 3 5 6 1 2 3 2 4 3 5 6 4 5 6 9 7 8 2 1 2 3 2 4 3 5 6 4 5 6 9 7 8 2 1 2 3 2 4 3 5 6 4 5 6 9 7 8 2

[Interactions]

1.Setting up the learning context 2.Demonstrating how to solve a problem 3.Clarify the problem 4.Monitoring 5.Notifying how the learner is 6.Instigating thinking 7.Requesting problem’s details 8.Showing a solution 9.Affirmative reaction

GMIP - Growth Model Improved by Interaction Patterns

SLIDE 17

Collaborative Learning Authoring Tool

Anchored Instruction

Learning by Being Taught

LPP

Learning by Practice

Anchored Instruction

Learning by Diagnosing

Search Results Interaction Pattern

SLIDE 18

CL apprentice master

• bserver
• bserver

agent learner

Individual Learning Mode Collaborative Learning Mode

Opportunistic Group Formation

Design of activities Applications: Effective group formation/ Design of activities/ Interaction analysis Interaction analysis

[Ikeda et al., 99] Broadcasting a request Negotiation Group formation

SLIDE 19

We have been using ontologies to establish a common understanding of what a learning theory is by representing it in terms of its explicitness, formalism, concepts and vocabulary. This makes theories understandable and sharable, both by computers and humans. We use previous achievements in using ontologies for CL to clarify how interactions can affect learner’s development to propose another model, called GMIP. Explicitly identify the relationships among interaction patterns, learning strategies and learning goals. For users the GMIP allows the graphical visualization and use of learning

• theories. Thus, users can quickly interpret the theories, their benefits and

can propose sequence of activities in compliance with them. For computers, it provides a formal structure which allows systems to reason

• n learning theories to support effective group formation, the design of

group activities and the analysis of interactions. Re-formation of groups based on effective interaction analysis and accumulation of knowledge.

Conclusions

SLIDE 20

Thank you!

Seiji Isotani

isotani@acm.org

Riichiro Mizoguchi

mizoguchi@ei.sanken.osaka-u.ac.jp

The Institute of Scientific and Industrial Research Osaka University, Japan

(advisor)