10/15/2006 1elearn 2006 varscope personalized guidance for example selection in an explanatory...

11
10/15/2006 1 ELearn 2006 VARScope VARScope Personalized Guidance Personalized Guidance for Example Selection for Example Selection in an Explanatory in an Explanatory Visualization System Visualization System Dr. Peter Brusilovsky & Gayathri Krishnamoorthy School of Information Sciences University of Pittsburgh, Pittsburgh, PA October 15, 2006

Upload: roger-arnold

Post on 19-Jan-2016

220 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: 10/15/2006 1ELearn 2006 VARScope Personalized Guidance for Example Selection in an Explanatory Visualization System Dr. Peter Brusilovsky & Gayathri Krishnamoorthy

10/15/2006 1ELearn 2006

VARScopeVARScope

Personalized Guidance Personalized Guidance for Example Selection for Example Selection

in an Explanatory Visualization in an Explanatory Visualization SystemSystem

Dr. Peter Brusilovsky & Gayathri Krishnamoorthy

School of Information Sciences

University of Pittsburgh, Pittsburgh, PA

October 15, 2006

Page 2: 10/15/2006 1ELearn 2006 VARScope Personalized Guidance for Example Selection in an Explanatory Visualization System Dr. Peter Brusilovsky & Gayathri Krishnamoorthy

10/15/2006 2ELearn 2006

IntroductionIntroduction Program Visualization – key in computer Program Visualization – key in computer

science educationscience education Explanatory Visualization is one step ahead, Explanatory Visualization is one step ahead,

augmenting visualization with natural augmenting visualization with natural language explanations.language explanations.

Explanations on the flyExplanations on the fly Pre-authored explanations (most common, easy to create)Pre-authored explanations (most common, easy to create)

Growing tremendously every yearGrowing tremendously every year

Problem to students: Which is the best example for me?

Page 3: 10/15/2006 1ELearn 2006 VARScope Personalized Guidance for Example Selection in an Explanatory Visualization System Dr. Peter Brusilovsky & Gayathri Krishnamoorthy

10/15/2006 3ELearn 2006

Focus of the PaperFocus of the Paper

Solution for the example selection Solution for the example selection problemproblem

Personalized guidance using adaptive link Personalized guidance using adaptive link annotation in the form of visual cuesannotation in the form of visual cues

Way to enhance an existing Way to enhance an existing explanatory visualization system with explanatory visualization system with personalized guidance functionalitypersonalized guidance functionality

Using an available student model server (eg., Using an available student model server (eg., CUMULATE)CUMULATE)

Providing an adaptive panelProviding an adaptive panel

Page 4: 10/15/2006 1ELearn 2006 VARScope Personalized Guidance for Example Selection in an Explanatory Visualization System Dr. Peter Brusilovsky & Gayathri Krishnamoorthy

10/15/2006 4ELearn 2006

VARScope - FeaturesVARScope - Features Variable Scope is one of the critical Variable Scope is one of the critical

topics in introductory programming topics in introductory programming courses (Instructor’s survey) courses (Instructor’s survey)

VARScope guides students in learning VARScope guides students in learning the concept of “variable scope” in C the concept of “variable scope” in C programming language by offeringprogramming language by offering Personalized guidance in choosing the best Personalized guidance in choosing the best

exampleexample Visualizing the progress made on various concepts Visualizing the progress made on various concepts

using progress barsusing progress bars Explanatory visualization of pre-authored examplesExplanatory visualization of pre-authored examples

Page 5: 10/15/2006 1ELearn 2006 VARScope Personalized Guidance for Example Selection in an Explanatory Visualization System Dr. Peter Brusilovsky & Gayathri Krishnamoorthy

10/15/2006 5ELearn 2006

VARScope – Interface VARScope – Interface

Page 6: 10/15/2006 1ELearn 2006 VARScope Personalized Guidance for Example Selection in an Explanatory Visualization System Dr. Peter Brusilovsky & Gayathri Krishnamoorthy

10/15/2006 6ELearn 2006

VARScope - InterfaceVARScope - Interface

AdaptiAdaptive ve

PanelPanel

1

2

3

1. Annotated Links

2. Concept Grid

3. Progress Bars

Page 7: 10/15/2006 1ELearn 2006 VARScope Personalized Guidance for Example Selection in an Explanatory Visualization System Dr. Peter Brusilovsky & Gayathri Krishnamoorthy

10/15/2006 7ELearn 2006

Concepts and IndexingConcepts and Indexing

6 Domain 6 Domain concepts were concepts were identifiedidentified

Global, Local, Static, Global, Local, Static, Block Scope, Block Scope, Parameter & ExternParameter & Extern

Each example line Each example line was indexed with was indexed with these conceptsthese concepts

Problem# Line# Concepts

p6 5 local

p6 6 local

p6 9 parameter

p6 11 static

p6 12 parameter

p6  12  static

p6 13 static

Page 8: 10/15/2006 1ELearn 2006 VARScope Personalized Guidance for Example Selection in an Explanatory Visualization System Dr. Peter Brusilovsky & Gayathri Krishnamoorthy

10/15/2006 ELearn 2006 8

VAR Scope

Initiator

Servlet

Applet

Relay Servlet

3. User, group, progress

1. Html Link

(user, group)2. Initial Progress?

USER

MODEL

4. User events 5. User events

ImplementationImplementation

6. Problem Suggestion , progress ADAPT2

Protocol

6. Progress, problems explored

Page 9: 10/15/2006 1ELearn 2006 VARScope Personalized Guidance for Example Selection in an Explanatory Visualization System Dr. Peter Brusilovsky & Gayathri Krishnamoorthy

10/15/2006 9ELearn 2006

Personalized Example Personalized Example SuggestionSuggestion

Example suggestion is influenced byExample suggestion is influenced by1.1. Difficulty level of the example Difficulty level of the example

Proportional to the number of domain conceptsProportional to the number of domain concepts Level 1, 2, 3 or 4, with level 1 on the easier side Level 1, 2, 3 or 4, with level 1 on the easier side

suitable for first-time explorationsuitable for first-time exploration

2.2. User’s current knowledge of the domain User’s current knowledge of the domain conceptsconcepts

3.3. Comfort level of the userComfort level of the user Calculated based on number of examples Calculated based on number of examples

explored under each difficulty levelexplored under each difficulty level Corresponds to one of the difficulty levels of the Corresponds to one of the difficulty levels of the

exampleexample

Page 10: 10/15/2006 1ELearn 2006 VARScope Personalized Guidance for Example Selection in an Explanatory Visualization System Dr. Peter Brusilovsky & Gayathri Krishnamoorthy

10/15/2006 10ELearn 2006

Personalized Example Personalized Example SuggestionSuggestion

Appropriate examplesAppropriate examples Examples unexplored under user’s Examples unexplored under user’s

current comfort levelcurrent comfort level If all examples under current comfort If all examples under current comfort

level is explored, suggest examples level is explored, suggest examples from subsequent higher difficulty levelfrom subsequent higher difficulty level

In-appropriate examplesIn-appropriate examples Examples whose difficulty level is Examples whose difficulty level is much much

higher higher than the user’s comfort levelthan the user’s comfort level

Page 11: 10/15/2006 1ELearn 2006 VARScope Personalized Guidance for Example Selection in an Explanatory Visualization System Dr. Peter Brusilovsky & Gayathri Krishnamoorthy

10/15/2006 11ELearn 2006

EvaluationEvaluation QuestionnaireQuestionnaire

6 users evaluated VARScope, shared their experience by filling 6 users evaluated VARScope, shared their experience by filling out our questionnaire which captured user’s perception onout our questionnaire which captured user’s perception on

Easy navigabilityEasy navigability Learning goal achievementLearning goal achievement Interface DesignInterface Design Ability to visualize progressAbility to visualize progress Problem SuggestionProblem Suggestion Amount of Help providedAmount of Help provided

Think-aloudThink-aloud3 think-aloud studies3 think-aloud studies

were performedwere performed

0%

10%

20%

30%

40%

50%

60%

70%

80%

90%

100%

Easi

lyNa

viga

ble

Lear

ning

Goa

lAc

hiev

ed

Inte

rface

Desi

gn

Abilit

y to

see

prog

ress

Prob

lem

Sugg

estio

n

Amou

nt o

fHe

lp p

rovi

ded

StronglyDisagree

Disagree

Neutral

Agree

Strongly Agree