Learning objects retrieval from contextual analysis of user preferences to enhance e-learning personalization

Campus Sorocaba
Learning Objects Retrieval fromLearning Objects Retrieval from
Contextual Analysis of User PreferencesContextual Analysis of User Preferences
to Enhance E-learning Personalizationto Enhance E-learning Personalization
LERIS-Laboratory of Studies in Networks, Innovation and Software
www.leris.sor. ufscar.br
Federal University of São Carlos - Sorocaba, Brazil
Luciana A M Zaina and Graça Bressan
Available in:
• Draft: http://www.dcomp.sor.ufscar.br/lzaina/papers/ICWI2009_draft.pdf
• Final version: http://connection.ebscohost.com/c/articles/63798599/learning-objects-retrieval-
from-contextual-analysis-user-preferences-enhance-e-learning-personalization

IntroductionIntroduction
 The personalization of a learning process occurs
through the investigation of the student’s preferences by
tracking his interaction with the environment.
 Adherence to the user’s preferences and to the
content exhibited to the student may be enhanced by
correlating learning objects and learning styles.
 The observation of learning styles is one of the
techniques that provide users with different teaching
strategies, meeting the student’s individual needs.

Paper ObjectivePaper Objective
 To present a mechanism to retrieve learning objects
based on the analysis of user preference data from
contextual information about student interactions.
 This mechanism is performed by a component of a
system architecture and it is based on the student’s
classification in a specific learning profile.
 Felder and Silverman Model is adopted to classify
the student learning profile.
 A relationship between the categories of preferences
and the learning objects is used to build automatically
the learning scenarios according to the student learning
profile.

E-Learning Personalization IssuesE-Learning Personalization Issues
 Important issues to support personalization:
 Learning objects
 User preferences
 Context-aware applications

Learning ObjectLearning Object
 It can be defined as an entity to be applied in a teaching-
learning process.
 e-learning: the aim is to create contents in digital formats.
 Metadata usually is adopted to organize learning objects,
improving their reuse.
 The LOM (Learning Object Metadata) standard of the Institute
of Electrical and Electronics Engineers – IEEE is the metadata
specification used in the area of learning objects.
 It has a structure that describes learning objects through
descriptor categories.

Examples of LOM CategoriesExamples of LOM Categories
LOM Category LOM Field Characterization
Technical Media Format (video
type, sound)
Technical features
description.
Size
Physical location
Requirements (object
use: software version, for
example)
Educational Interactive type (active,
expositive) Educational function
and pedagogical
characteristics object description.
Learning Resource Type
(exercise, simulation,
questionnaire)

User PreferencesUser Preferences
 The user preferences may be observed through his learning
style.
 The learning style involves the strategies that a student
tends to apply frequently to a given teaching situation.
 The Felder-Silverman Learning Style Model is describe by
dimensions of Learning and Teaching Styles, creating a
relationship to learning styles and teaching strategies that
could be adopted to support the student learning style.
 The Felder-Silverman model was selected to this work,
because it's close relationship to learning styles and teaching
strategies, resulting in an adherence between these aspects.

Dimensions of Felder-SilvermanDimensions of Felder-Silverman
Learning Style ModelLearning Style Model
Learning Style Teaching
Strategies
Features
sensory concrete It is related with the perception of
content.intuitive abstract
visual visual It is related with the format of
content presentation.auditory verbal
active active It is related with the student
participation in the activities.reflective passive
sequential sequential It is related with the best order to
present the content: step-by-step
progression or a overview first of
content.
global global

Context-aware applicationsContext-aware applications
 They were developed in the field of ubiquitous
computation.
 Context is used to characterize a given interactive
situation.
 A set of relevant conditions and influences in the
interaction.
 It may support the dynamic composition of an
application offering suitable services and information
to the user.

E-LearningE-Learning ArchitectureArchitecture
 This paper proposal is based on the presented
architecture:

LearnPESLearnPES
 Learning Profile Evaluation System.
 It is responsible for modeling the learning profile, providing the
Monitoring API with the features used during the observation of
the student’s interaction.
 It suggests the learning profile based on contextual information
and learning style models previously defined by the teacher.
LearnPES
Context
Information
Learning
Profile Models
Student Model
Monitoring
API
Observable
features
Suggested learning
profile

Step I -Step I - LearnPESLearnPES
 The teacher will determine the relevant observable
features.
 One observable feature will reflect the student preference
about the feature. Because of this the teacher must
classify, during the observation planning, each observable
feature in one of categories of preferences: Perception,
Presentation Format, Presentation Order or Participation.
These categories are adherent to dimensions of Felder-
Silverman Learning Style Model.
 The group of observable features will compose an
Observation Model. The Observation Model will send to
Monitoring Module to be used by tracking the student
interaction in the e-learning environment.

Step II -Step II - LearnPESLearnPES
 The next step is the values specification for each observed
feature determining the learning profile types that will be
adopted during classification process.
 The values permit the system to distinguish the different
types of learning profile considering the variety of
observable features.
 The teacher may specify the characteristics of each type
of learning profile for the categories of preference used in
the observed feature definition.

Step III - LearnPESStep III - LearnPES
 When a student completes a teaching module, the
monitoring module triggers an event to LearnPES,
notifying it of the conclusion of the process and informing
it who is involved in the interaction.
 Based on this information, the LearnPES consolidates the
contextual information about the student’s interaction.
 The result of this consolidation will determine the values
of each item described in the observable feature for a
specific student, thus providing information to determine
the student profile.
 Then LearnPES suggests the learning profile,
categorizing the user preferences.

Step IV - LearnPESStep IV - LearnPES
 After classifying the student according to a
learning profile, the LearnPES triggers an event
to the LearnSBuilder to start the retrieval
process.

LearnSBuilderLearnSBuilder
 It uses the categories of preferences to retrieve
the learning objects.
 It makes a correlation between the categories of
preferences (present in the student model) and
the fields of LOM.
Learning Objects
Student Model
LearnSBuilder

Component to retrieve LOComponent to retrieve LO
 The component carries out searches in
repositories containing objects catalogued
according to the LOM standard.
 The maintenance of learning object repositories
must be supported by the e-learning
infrastructure that adopts the proposed
architecture.

Learning Objects retrieval processLearning Objects retrieval process
Steps to localize
learning objects
LOM fields LOM Category
Title, Description,
and Keywords
Location of
concepts
General
Finding the objects
that match the
student’s learning
profile
Interactivity and
Learning
Resource
Educational
LOLearning Objects
selected
LO
LO
LO
LO
Steps to localize
learning objects
LOM fields LOM Category
Title, Description,
and Keywords
Location of
concepts
General
Finding the objects
that match the
student’s learning
profile
Interactivity and
Learning
Resource
Educational
LOLearning Objects
selected
LO
LO
LO
LO

Step I - Location of conceptsStep I - Location of concepts
 To this end, the search component looks for the subject
into the “General” category of the LOM specification by
means of the fields: Title, Description, and Keywords.
 The result is a LO set related to the subject.

 It uses the “Educational” category (Interactivity and Learning
Resource fields).
 It identifies the objects that match the preferences related to
the student’s learning profile in the set of objects obtained in
the first locating step.
Step II – Location based on learningStep II – Location based on learning
profileprofile

LOM fields X Preference CategoriesLOM fields X Preference Categories
LOM Field Field Values
Profile
Feature
Preference
Category
Interactivity
Active Concrete
Perception
Expositive Abstract
Learning
Resource
Figure, Video, Film, and
others
Visual
Presentation-
FormatText, Sound, and others Auditory
Practical Exercise,
Experiment, and others
Active
Participation
Questionnaire, and
Readings
Reflexive

Evaluation of the proposed mechanismEvaluation of the proposed mechanism
 The mechanism was evaluated in an experiment applied
in a group of Computer Engineering students during a
Data Structure course.
 The purpose of the experiment is to motivate the learners
to complement their studies in a virtual environment.
 During four months, the students will have access to extra
material composed of videos, simulations, conceptual
texts, case studies, objective tests, sounds, etc.

Conclusions and future worksConclusions and future works
 The development of flexible educational environments
that are adaptable has become an important requisite
within the teaching-learning process.
 The association between learning profiles and learning
objects metadata grants dynamism in the content
retrieval process.
 Future directions:
 One important subject for future work is to extend
the architecture to considering to the retrieval
mechanism the features of mobile learning as
differences between devices.

Campus Sorocaba
Thanks!Thanks!
lzaina@ufscar.brlzaina@ufscar.br
http://www.dcomp.sor.ufscar.br/lzainahttp://www.dcomp.sor.ufscar.br/lzaina

Learning objects retrieval from contextual analysis of user preferences to enhance e-learning personalization

More Related Content

Viewers also liked

Similar to Learning objects retrieval from contextual analysis of user preferences to enhance e-learning personalization

More from Luciana Zaina

Recently uploaded

Learning objects retrieval from contextual analysis of user preferences to enhance e-learning personalization

Editor's Notes