protus 2.0: ontology-based semantic recommendation in programming tutoring system

28
1 Protus 2.0: Ontology-based semantic recommendation in programming tutoring system Presentor: Boban Vesin Boban Vesin, Aleksandra Klašnja-Milićević Higher School of Professional Business Studies Novi Sad, Serbia e-mail: {vesinboban, aklasnja}@yahoo.com Mirjana Ivanović, Zoran Budimac Department for Mathematics and Informatics Faculty of Science, Novi Sad, Serbia e-mail: {mira, zjb}@dmi.uns.ac.rs atija, Croatia, 2012.

Upload: gwyn

Post on 06-Jan-2016

39 views

Category:

Documents


0 download

DESCRIPTION

Opatija, Croatia, 2012. Boban Vesin, Aleksandra Kla šnja-Milićević Higher School of Professional Business Studies Novi Sad, Serbia e-mail: {vesinboban , aklasnja } @yahoo.com Mirjana Ivanović, Zoran Budimac Department for Mathematics and Informatics Faculty of Science, Novi Sad, Serbia - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Protus 2.0: Ontology-based semantic recommendation in programming tutoring system

1

Protus 2.0: Ontology-based semantic recommendation in programming

tutoring system

Presentor: Boban Vesin

Boban Vesin, Aleksandra Klašnja-Milićević Higher School of Professional Business Studies

Novi Sad, Serbiae-mail: {vesinboban, aklasnja}@yahoo.com

Mirjana Ivanović, Zoran Budimac Department for Mathematics and Informatics

Faculty of Science, Novi Sad, Serbiae-mail: {mira, zjb}@dmi.uns.ac.rs

Opatija, Croatia, 2012.

Page 2: Protus 2.0: Ontology-based semantic recommendation in programming tutoring system

2

Contents

• Introduction

• Personalization of content

• Used technologies

• Protus 2.0 architecture

• Ontologies in Protus 2.0

• Implemented rules

• Learner’s interface

• Conclusion

Page 3: Protus 2.0: Ontology-based semantic recommendation in programming tutoring system

3

Introduction

• Semantic Web technologies

• Educational environments

• Ontologies

• Ontologies provide a vocabulary of terms whose semantics are formally specified

• Ontologies need additional rules to make further inferences

Into Personalisation Technologies Arcitecture Ontologies Rules Interface Conlusion

Page 4: Protus 2.0: Ontology-based semantic recommendation in programming tutoring system

4

Introduction• The major goal of learning systems is to support a

given pedagogical strategy

• Ontologies can be associated with reasoning mechanisms and rules to enforce a given adaptation strategy in learning system

• Protus - PRogramming TUtoring System

• Adaptation of the teaching material and navigation in a course based on the principles of Learning styles recognition for a particular learner

• The main objective of the presentation is to present new version of Protus that completely relis on Semantic web technologies

Into Personalisation Technologies Arcitecture Ontologies Rules Interface Conlusion

Page 5: Protus 2.0: Ontology-based semantic recommendation in programming tutoring system

5

Personalization of content

• Customization of content to match characteristics specified by the learner model

• Protus 2.0 provides two general categories of personalization based on recommender systems– Content adaptation – Learner interface adaptation

• Adaptation based on the learning style of the learner

Into Personalisation Technologies Arcitecture Ontologies Rules Interface Conlusion

Page 6: Protus 2.0: Ontology-based semantic recommendation in programming tutoring system

6

Learning styles identification

• Index of Learning Styles (ILS)• ILS assesses variations in individual learning

style preferences across four dimensions or domains:– Information Processing: Active and Reflective

learners,– Information Perception: Sensing and Intuitive

learners,– Information Reception: Visual and Verbal learners, – Information Understanding: Sequential and Global

learners.

Into Personalisation Technologies Arcitecture Ontologies Rules Interface Conlusion

Page 7: Protus 2.0: Ontology-based semantic recommendation in programming tutoring system

7

Characteristics of learners

Active Reflective

Work in groups Work alone

Preference to try out new material immediately (Ask, discuss, and explain)

Preference to take time to think about a problem

Practical (Experimentalists) Fundamental (Theoreticians) Sensing Intuitive

More patient with details More interested in overviews and a broad knowledge (bored with details)

By standard methods Innovations Senses, facts and experimentation Perception, principles and theories Visual Verbal Preference to perceive materials as pictures, diagrams and flow chart

Preference to perceive materials as text

Global Sequential

Prefer to get the big picture first Prefer to process information sequentially Assimilate and understand information in a linear and incremental step, but lack a grasp of the big picture

Absorb information in unconnected chunks and achieve understanding in large holistic jumps without knowing the details

Into Personalisation Technologies Arcitecture Ontologies Rules Interface Conlusion

Page 8: Protus 2.0: Ontology-based semantic recommendation in programming tutoring system

8

Used technologies

• OWL - Ontology Web Language

• Protégé - ontology editor – SWRLTab

• SWRL - Semantic Web Rule Language

Into Personalisation Technologies Arcitecture Ontologies Rules Interface Conlusion

Page 9: Protus 2.0: Ontology-based semantic recommendation in programming tutoring system

9

Protus

• Different courses and domains

• Highly modular architecture

• Five central components: – the application module– the adaptation module– the learner model– session monitor– domain module

Into Personalisation Technologies Arcitecture Ontologies Rules Interface Conlusion

Page 10: Protus 2.0: Ontology-based semantic recommendation in programming tutoring system

10

Overall architecture of Protus

Session monitor

Application module

Adaptation module Domain module

Learner model

Learner’s interface(interface ontology)

Server side of systemLearner model

ontology

Domain ontology

Task ontology

Teacher’s interface

Teaching strategy ontology

Communication ontology define conection between components

Into Personalisation Technologies Arcitecture Ontologies Rules Interface Conlusion

Page 11: Protus 2.0: Ontology-based semantic recommendation in programming tutoring system

11

An excerpt of domain ontology

Into Personalisation Technologies Arcitecture Ontologies Rules Interface Conlusion

Page 12: Protus 2.0: Ontology-based semantic recommendation in programming tutoring system

12

An excerpt of resource topology

Into Personalisation Technologies Arcitecture Ontologies Rules Interface Conlusion

Page 13: Protus 2.0: Ontology-based semantic recommendation in programming tutoring system

13

Learner model ontology

Into Personalisation Technologies Arcitecture Ontologies Rules Interface Conlusion

Page 14: Protus 2.0: Ontology-based semantic recommendation in programming tutoring system

14

Ontology for learner observation

Into Personalisation Technologies Arcitecture Ontologies Rules Interface Conlusion

Page 15: Protus 2.0: Ontology-based semantic recommendation in programming tutoring system

15

Teaching Strategy ontology

Class

Personalization

Class

LearningStyle

Class

Condition

Class

AdaptationTypeClass

CurrentGoal

Class

NavigationSequence

Class

Resouce

Class

BehaviourPattern

Class

Decision

Class

Performance

determines

basedOn

generates

generates

Class

Learner

hasLearningStyle

has Performance

isTypeOf

basedOn

basedOn

consistsOf isTypeOf

Into Personalisation Technologies Arcitecture Ontologies Rules Interface Conlusion

Page 16: Protus 2.0: Ontology-based semantic recommendation in programming tutoring system

16

Implemented rules

• In Protus:– the interface elements for sequential

navigation are hidden/shown– Different presentation methods – Adding of links to related or more complex

content

• Three groups of rules:– learner-system interaction rules– off-line rules– recommendation rules

Into Personalisation Technologies Arcitecture Ontologies Rules Interface Conlusion

Page 17: Protus 2.0: Ontology-based semantic recommendation in programming tutoring system

17

Examle of implemented rules

• The form of the rules:antecedent -> consequent

• Following rule updates learner model:Learner(?x) Interaction(?y) hasInteraction(?x,?y) Concept(?c) conceptUsed(?y,?c) Performance(?p) hasResult(?y,?p) hasGrade(?p,?m) swrlb:greaterThan(?m, 1) isLearned(?c, true) hasPerformance(?x,?p)

Into Personalisation Technologies Arcitecture Ontologies Rules Interface Conlusion

Page 18: Protus 2.0: Ontology-based semantic recommendation in programming tutoring system

18

User Interface of Protus

• Web pages for students

– online tutorial with numerous resources

– testing knowledge

– communication with teachers and other students

• Learning styles identification

• Initial assessment is based on the ILS Questionnaire

Into Personalisation Technologies Arcitecture Ontologies Rules Interface Conlusion

Page 19: Protus 2.0: Ontology-based semantic recommendation in programming tutoring system

19

ILS Questionnaire

Into Personalisation Technologies Arcitecture Ontologies Rules Interface Conlusion

Page 20: Protus 2.0: Ontology-based semantic recommendation in programming tutoring system

20

Result of ILS questionnaire

Into Personalisation Technologies Arcitecture Ontologies Rules Interface Conlusion

Page 21: Protus 2.0: Ontology-based semantic recommendation in programming tutoring system

21

Information Processing:

User interface for Activists

User interface for Reflectors

Into Personalisation Technologies Arcitecture Ontologies Rules Interface Conlusion

Page 22: Protus 2.0: Ontology-based semantic recommendation in programming tutoring system

22

Information Perception

• Recommendation of Additional material option for Sensing learners

• Recommendation of Syntax rules option to Intuitive learner

Into Personalisation Technologies Arcitecture Ontologies Rules Interface Conlusion

Page 23: Protus 2.0: Ontology-based semantic recommendation in programming tutoring system

23

Information Reception:

• Example of lesson for Visual learners

Into Personalisation Technologies Arcitecture Ontologies Rules Interface Conlusion

Page 24: Protus 2.0: Ontology-based semantic recommendation in programming tutoring system

24

Information Reception:

• Example of lesson for Verbal learners

Into Personalisation Technologies Arcitecture Ontologies Rules Interface Conlusion

Page 25: Protus 2.0: Ontology-based semantic recommendation in programming tutoring system

25

Information Understanding

• Elements for Global Learners

• Navigation for Sequential learners

Into Personalisation Technologies Arcitecture Ontologies Rules Interface Conlusion

Page 26: Protus 2.0: Ontology-based semantic recommendation in programming tutoring system

26

User interface of Protus 2.0

Into Personalisation Technologies Arcitecture Ontologies Rules Interface Conlusion

Page 27: Protus 2.0: Ontology-based semantic recommendation in programming tutoring system

27

Conclusion

• We presented how Semantic Web technologies and in particular ontologies can be used for building Java tutoring system

• Architecture for such adaptive and personalized tutoring system that completely relies on Semantic Web technologies was presented

Into Personalisation Technologies Arcitecture Ontologies Rules Interface Conlusion

Page 28: Protus 2.0: Ontology-based semantic recommendation in programming tutoring system

28

Protus 2.0: Ontology-based semantic recommendation in programming

tutoring system

Presentor: Boban Vesin

Boban Vesin, Aleksandra Klašnja-Milićević Higher School of Professional Business Studies

Novi Sad, Serbiae-mail: {vesinboban, aklasnja}@yahoo.com

Mirjana Ivanović, Zoran Budimac Department for Mathematics and Informatics

Faculty of Science, Novi Sad, Serbiae-mail: {mira, zjb}@dmi.uns.ac.rs

Opatija, Croatia, 2012.