24
Next Generation eLearning Can Technology Learn from the Learners: The case for Adaptive Learning Objects Vincent Wade Research Director, Knowledge & Data Engineering Research Group Computer Science Dept. Trinity College Dublin www.cs.tcd.ie/kdeg Director Center for Learning Technology Trinity College Dublin www.tcd.ie/clt

Next Generation eLearning Can Technology Learn from the Learners: The case for Adaptive Learning Objects Vincent Wade Research Director, Knowledge & Data

  • View
    213

  • Download
    0

Embed Size (px)

Citation preview

Page 1: Next Generation eLearning Can Technology Learn from the Learners: The case for Adaptive Learning Objects Vincent Wade Research Director, Knowledge & Data

Next Generation eLearningCan Technology Learn from the Learners:The case for Adaptive Learning Objects

Vincent WadeResearch Director,

Knowledge & Data Engineering Research Group

Computer Science Dept.Trinity College Dublin

www.cs.tcd.ie/kdeg

DirectorCenter for Learning Technology

Trinity College Dublinwww.tcd.ie/clt

Page 2: Next Generation eLearning Can Technology Learn from the Learners: The case for Adaptive Learning Objects Vincent Wade Research Director, Knowledge & Data

© Vincent P. Wade Adaptive Personalised eLearning 2

Student Centric e-Learning

Goal of Adaptive, Personalised e-Learning:

“to provide e-learning content, activities and collaboration,

adapted to the specific needs and influenced by specific preferences and context of the student,

based on the sound pedagogic strategies”

Page 3: Next Generation eLearning Can Technology Learn from the Learners: The case for Adaptive Learning Objects Vincent Wade Research Director, Knowledge & Data

© Vincent P. Wade Adaptive Personalised eLearning 3

What does it offer the learner?

What does it offer the teacher?

Some Questions?

How difficult is it to achieve?

Does it need an army of engineers, developers And subject matter experts?

What is Adaptive, Personalised eLearning?

What record of success does it have?

Page 4: Next Generation eLearning Can Technology Learn from the Learners: The case for Adaptive Learning Objects Vincent Wade Research Director, Knowledge & Data

© Vincent P. Wade Adaptive Personalised eLearning 4

Motivation

• ‘One size doesn’t fit all’!– Different people have different needs, likes,

preferences, skills, abilities– Are in different locations, using different devices,

With different connectivity – Are in different circumstances, using service for

different reasons ……

• Large variety of Users, very variable circumstances, large ‘hyper’space

Page 5: Next Generation eLearning Can Technology Learn from the Learners: The case for Adaptive Learning Objects Vincent Wade Research Director, Knowledge & Data

© Vincent P. Wade Adaptive Personalised eLearning 5

Motivation

• Digital Content very expensive to develop=> need to ensure re-use

• Need to automate ‘transformation’ process of digital content - to ensure greater usability

Page 6: Next Generation eLearning Can Technology Learn from the Learners: The case for Adaptive Learning Objects Vincent Wade Research Director, Knowledge & Data

Adapt to Learner’s …

Learner

Prior Knowledge & ExpertisePrior Knowledge & Expertise

Cognitive &Cognitive &

Learning StyleLearning Style

Learning History

Aims and GoalsAims and Goals

Preferences &

Learning Culture

Communication

Style & Needs

Page 7: Next Generation eLearning Can Technology Learn from the Learners: The case for Adaptive Learning Objects Vincent Wade Research Director, Knowledge & Data

Some Examples …...

Page 8: Next Generation eLearning Can Technology Learn from the Learners: The case for Adaptive Learning Objects Vincent Wade Research Director, Knowledge & Data

© Vincent P. Wade Adaptive Personalised eLearning 8

Benefits of Personalised e-Learning

• Pedagogic

– Improved quality & effectiveness (no two students are identical)

– Improved Relevancy

– Reduced cognitive overload, reduced learning time

– Improve retention

– Empower learner (take more responsibility, more active participation)

Page 9: Next Generation eLearning Can Technology Learn from the Learners: The case for Adaptive Learning Objects Vincent Wade Research Director, Knowledge & Data

© Vincent P. Wade Adaptive Personalised eLearning 9

Benefits of Personalised e-Learning

• Management

– Promote Resource (content) Reuse / Reduced Costs

– Ability to introduce Multiple courses across same content repository

– Enable further e-learning opportunities

Page 10: Next Generation eLearning Can Technology Learn from the Learners: The case for Adaptive Learning Objects Vincent Wade Research Director, Knowledge & Data

© Vincent P. Wade Adaptive Personalised eLearning 10

Adapting to What?

• Knowledge about the subject• Knowledge about the system • Goals• Interests• Culture• Language• Capabilities• (Dis)Abilities• Preferences

Learner

Page 11: Next Generation eLearning Can Technology Learn from the Learners: The case for Adaptive Learning Objects Vincent Wade Research Director, Knowledge & Data

© Vincent P. Wade Adaptive Personalised eLearning 11

Case Study: Trinity College Dublin

• Engineering Faculty: Dept. of Computer Science

• 7 Different Degrees

– Computer Engineering,Computer Science, Info. Technology etc.

• Various ‘Databases’ courses taught on different degree, to different student years (1st - 4th ), with varying learning objectives & syllabi

Page 12: Next Generation eLearning Can Technology Learn from the Learners: The case for Adaptive Learning Objects Vincent Wade Research Director, Knowledge & Data

© Vincent P. Wade Adaptive Personalised eLearning 12

Multi-model, Metadata Driven Approach

• Metadata to describe Adaptive Resources

• Multi-model

• Two versions of the approach– 3 Models – Content, Learner and Narrative (PLS)– N Models – At least one Narrative, the rest are

metadata based (APeLS)

• User Trial and Feedback

Page 13: Next Generation eLearning Can Technology Learn from the Learners: The case for Adaptive Learning Objects Vincent Wade Research Director, Knowledge & Data

© Vincent P. Wade Adaptive Personalised eLearning 13

The Learner Model

• The Learner Model contains information about the Learner’s …– Pre-knowledge (Prior Knowledge)– Objectives and Goals– Cognitive and Learning Style

LearnerModel

Pre-knowledge

Objectives

Learning Style

Page 14: Next Generation eLearning Can Technology Learn from the Learners: The case for Adaptive Learning Objects Vincent Wade Research Director, Knowledge & Data

© Vincent P. Wade Adaptive Personalised eLearning 14

The Content Model (Learning Objects)

• The Content Model must accurately represent the unit of material (a fine grained LO)

• The model must represent each LO from three perspectives…– General Information– Pedagogical Information– Technical Information

Page 15: Next Generation eLearning Can Technology Learn from the Learners: The case for Adaptive Learning Objects Vincent Wade Research Director, Knowledge & Data

© Vincent P. Wade Adaptive Personalised eLearning 15

The Narrative Model (cont.)

• The Narrative Model representS relationships between CONCEPTS

• These relationships include…

– Pre-requisites

– Suggested optional concepts

Narrative Model

Start PointsRelationships

Page 16: Next Generation eLearning Can Technology Learn from the Learners: The case for Adaptive Learning Objects Vincent Wade Research Director, Knowledge & Data

Adaptive Service

Adaptive Personalised Learning Service (APeLS) Architecture

LearningObjectsModel

Learner

LearnerModel

LearningObject Mdl

Narrative LearnerModels

Learn

er P

orta

l

NarrativeModels

Page 17: Next Generation eLearning Can Technology Learn from the Learners: The case for Adaptive Learning Objects Vincent Wade Research Director, Knowledge & Data

© Vincent P. Wade Adaptive Personalised eLearning 17

The Personalised Learning Service - Reconciling the Models

• The Adaptive Engine must determine the core and optional material for the learner

LearnerModel

Pre-knowledge

Objectives

Learning Style

Learning ObjectModel

Keywords

Content Type

Supported Learning Style

Narrative Model

Start PointsRelationships

Page 18: Next Generation eLearning Can Technology Learn from the Learners: The case for Adaptive Learning Objects Vincent Wade Research Director, Knowledge & Data

© Vincent P. Wade Adaptive Personalised eLearning 18

Authoring AdaptivePersonalised eLearning

Course Design = Model Design + Learning ObjectAuthoring

• Development of Models– Concept Space (ontological approach)

– Narrative Model (pedagogic/Instructional design based models) e.g Case Based, Web Quests, Didactic, Learning Spaces etc.

– Adaptive Property selection

– Content (Learning Objects)

Page 19: Next Generation eLearning Can Technology Learn from the Learners: The case for Adaptive Learning Objects Vincent Wade Research Director, Knowledge & Data

• Course Design = Model Design + Leaning ObjectAuthoring

• Development of Models– Concept Space (ontological approach)

– Narrative Model (pedagogic/Instructional design based models) e.g Case Based, Web Quests, Didactic, Learning Spaces etc.

– Adaptive Property selection

– Content Piglets

Authoring AdaptivePersonalised eLearning Le

arn

er

Mod

el Le

arni

ng

Objec

t Mod

el

Narr

ati

ve M

od

el

ConceptModel

Context

Model

Learner

Page 20: Next Generation eLearning Can Technology Learn from the Learners: The case for Adaptive Learning Objects Vincent Wade Research Director, Knowledge & Data

© Vincent P. Wade Adaptive Personalised eLearning 20

Evaluation

• APeLS used to deliver RDBMS course to 120 final year students (two degrees)

• Pre-test instrument for VARK & prior knowledge in DBMS

• Learners able to rebuild their personalized course via instrumentation

• Highly popular with student body

• Continual refinement & re-personalization by student for various reasons

Page 21: Next Generation eLearning Can Technology Learn from the Learners: The case for Adaptive Learning Objects Vincent Wade Research Director, Knowledge & Data

© Vincent P. Wade Adaptive Personalised eLearning 21

8

9

10

11

12

13

14

15

1998 1999 2000 2001* 2002 2003

Year

Qu

es

tio

n S

co

re (

ou

t o

f 2

0)

Related Questions

Unrelated Questions

Average Question Scores on Database Examinations 1998 – 2003

Page 22: Next Generation eLearning Can Technology Learn from the Learners: The case for Adaptive Learning Objects Vincent Wade Research Director, Knowledge & Data

© Vincent P. Wade Adaptive Personalised eLearning 22

Student Opinions

• Very high satisfaction rating of course (87%)

• All students used the ‘adaptive’ controls to take responsibility for their e-learning

• 60% satisfied with level of control offered by the ‘adaptive’ controls

• Some interesting observations– frequent student re-personalisation for specific time

objective

Page 23: Next Generation eLearning Can Technology Learn from the Learners: The case for Adaptive Learning Objects Vincent Wade Research Director, Knowledge & Data

© Vincent P. Wade Adaptive Personalised eLearning 23

the story so far …

• Adaptive Hypermedia Services facilitates:– graceful enhancement and scalability of content

service– support multiple courses & learning experiences– empower user (learner)– interpretative Semantic Web driven approach allows

evolution of adaptivity

Page 24: Next Generation eLearning Can Technology Learn from the Learners: The case for Adaptive Learning Objects Vincent Wade Research Director, Knowledge & Data

© Vincent P. Wade Adaptive Personalised eLearning 24

Thank you…………

any questions ………