TAKING RICH CONTEXT AND SITUATION IN ACCOUNT FOR

IMPROVING AN ADAPTIVE E-LEARNING SYSTEM

Isabela Gasparini

1,2

, Ana Marilza Pernas

1,3

, Amel Bouzeghoub

José Palazzo M. de Oliveira

, José Valdeni de Lima

and Marcelo S. Pimenta

Instituto de Informática, Universidade Federal do Rio Grande do Sul, Porto Alegre, Brazil

Universidade do Estado de Santa Catarina, Joinville, Brazil

Universidade Federal de Pelotas, Pelotas, Brazil

TELECOM & Management SudParis, Evry, France

Keywords: Adaptation/Personalization, Cultural and context-aware, Situation-aware, e-Learning environments.

Abstract: Although there are several approaches for adaptive e-learning systems, they focus mainly on technological

and/or networking aspects without taking into account other contextual aspects, such as cultural and peda-

gogical context. This paper presents a context-aware situation-dependent personalization approach designed

for an adaptive e-learning system called AdaptWeb

, based on a rich context model as an extension to stu-

dent modeling.

1 INTRODUCTION

A Web-based e-learning system (ELS) is normally

used by a wide variety of students. Adaptive ELS

adjust the content, presentation and navigation to a

student's model. Personalization (or adaptation) is

the process of adapting a computer application to the

needs of specific user and takes advantage of the

acquired knowledge about him/her. ISO defines

usability as evaluated by the effectiveness,

efficiency and satisfaction which users achieve

specified goals in a particular context of use (ISO

9241, 1998). Specifically in an e-learning

environment: i) an user is typically someone

playing a student or a teacher role; ii) goals are

related to activities of learning process, by acquiring

new knowledge, behaviors, skills, preferences or

values, and may involve synthesizing different types

of information; and iii) differently from human-to-

human interactions, in human-to-computer

interactions, the context of use is usually described

by a set of (cultural, technological, pedagogical, etc.)

characteristics that are necessary to support the

learning process and its goals.

Since ELS are normally used by a wide variety

of students with different skills, background,

preferences, and learning styles, an ELS must

provide improved usability being adaptive and

personalized. Traditionally, the most widely used

components of student profiles have been considered

(Brusilovsky and Míllan, 2007): knowledge,

individual traits such as learning or cognitive styles,

experiences and background (Souto, 2002), goals or

tasks, as hierarchical task network planning

presented in Ullrich (2008). However, there are

other relevant criteria to reach personalization, such

as motivation, working memory capacity,

personality traits, behavior, culture, etc. (BROWN et

al. 2009). At the same time, ELSs may be

dynamically adjusted not only according to the

student’s model but also depending on a richer

notion of context. A contextualized ELS provides

the student with the material he needs, and

appropriate to his knowledge level and which makes

sense in a special learning situation, called a

scenario (Eyharabide et al., 2009), (Gasparini 2010).

The aim of our research is to investigate

approaches putting the users’ profile and contextual

information into practice in the development process

of the ELSs AdaptWeb

(Freitas et al. 2002), whose

goal is to adapt content, presentation and navigation

in an educational web course according to the

student model. AdaptWeb

is an open source

environment, available in SourceForge

This paper is organized as follows. Section 1

presents an overview of our research and objectives.

Section 2 explains some related works. Section 3

discusses our approach to modeling context and

165

Gasparini I., Marilza Pernas A., Bouzeghoub A., Palazzo M. de Oliveira J., Valdeni de Lima J. and S. Pimenta M..

TAKING RICH CONTEXT AND SITUATION IN ACCOUNT FOR IMPROVING AN ADAPTIVE E-LEARNING SYSTEM.

DOI: 10.5220/0003291001650172

In Proceedings of the 3rd International Conference on Computer Supported Education (CSEDU-2011), pages 165-172

ISBN: 978-989-8425-49-2

 2011 SCITEPRESS (Science and Technology Publications, Lda.)

culture. Section 4 introduces our extended

architecture. Section 5 illustrates some examples of

utilization. Finally, in section 6 we expose our

conclusions.

2 RELATED WORK

Research in adaptive educational hypermedia has

demonstrated that considering context leads to a

better understanding and personalization (Brusi-

lovsky and Míllan, 2007). Context is vital to im-

prove personalization in ELSs. Recent works aim to

provide the capacity for identifying the right con-

tents, right services in the right place at the right

time and in the right form based on the current stu-

dent´s situation. There is an interesting theory of

learning for a mobile society (Sharples et al., 2007)

but our work is closely related to others like (Bar-

bosa et al., 2006), (Yang et al. 2006), (MOBIlearn,

2003) and (Bouzeghoub, and Do Ngoc, 2008). The

interesting propositions of GlobalEdu (Barbosa et

al., 2006) in terms of architecture, for instance, have

distributed and central alternatives with different

models (student, context and environment).

An infrastructure to ubiquitous learning is pre-

sented in Tetchueng et al. (2007) where an environ-

ment to provide collaborative learning is proposed,

based on three systems: a peer-to-peer content

access and adaptation system; a personalized annota-

tion management system and a multimedia real-time

group discussion system.

Particularly about cultural aspects, Blanchard

and Mizoguchi (2008) describe an upper ontology of

culture, by working at the meta-level of culture.

They aim to identifying major constituents to be

considered when dealing with any kind of cultural

issue without having to endorse a particular culture’s

representational framework. They use this approach

to deal with many CATS (Culturally-Aware Tutor-

ing Systems) related issues by providing objective

formalism for cultural representation. Chandramouli

et al. (2008) presented the notion of the CAE-L On-

tology for modeling stereotype cultural artifacts in

adaptive education and used a Cultural Artifacts in

Education (CAE) questionnaire to gather the infor-

mation required to determine if there is a significant

cultural bias within online education, specifically

Adaptive Educational Hypermedia.

Motz et al. (2005) introduce an architecture in

the e-learning EduCa Project, based in a strong use

of ontologies for the retrieval, management and clus-

tered of electronic educational resources according

to user’s cultural aspects, like degree of impatience,

attitude, treatment, language, learning styles and

activities. These cultural aspects are specified in a

MultiCultural Aspects Ontology, which follows the

standard Learning Object Metadata (LOM) and uses

OWL (Web Ontology Language). Sieg et al. (2007)

presented a framework that integrates critical ele-

ments that make up the user context, namely the

user’s short-term behavior, semantic knowledge

from ontologies that provide explicit representations

of the domain of interest, and long-term user profiles

revealing interests and trends. They present a novel

approach for building ontological user profiles by

assigning interest scores to existing concepts in a

domain ontology.

Reinecke et al., (2007) present a Cultural User

Model Ontology (CUMO) that contains information

such as different places of residence, the parents’

nationality, languages spoken, and religion. Fur-

thermore, CUMO contains information about Hofs-

tede’s (Hofstede, 1991) national cultural dimensions.

Our research has a different point of view of

these works as we integrate cultural, technological,

pedagogical and personal aspects as part of a rich

context model (Eyharabide et al., 2009) that makes

sense in a special situation, in a given time. An im-

provement in the user’s contextual information leads

to a better understanding of users’ behavior in order

to adapt (i) the content, (ii) the interface, and (iii) the

assistance offered to users. A contextualized ELS

provides the student with exactly the material he

needs, and appropriate to his knowledge level and

that makes sense in a special learning situation.

However, while learning is a process intensively

related to the notion of situation, in most of ELSs

situation is only implicitly mentioned and not expli-

citly modeled. In order to support situation-aware

adaptation, it is necessary to model and specify both

context and situation. More accurately, there is a

complex intermeshing and continuous transforma-

tion of situations in combination with fluctuating

contexts, where meaning changes according to con-

text and through preferences of different partici-

pants. In this sense, e-learning personalization is

situation-dependent and cannot be managed in an

independent form.

3 APPROACH TO MODELING

CONTEXT AND CULTURE

In this section, our approach to model context and

culture in e-learning is described. Specially, we im-

proved the models used in the AdaptWeb

environ-

CSEDU 2011 - 3rd International Conference on Computer Supported Education

166

ment in order to incorporate the notion of context

and situation. We add a rich notion of context to

existing student profiles in order to provide a rich

personalization process. To be effective, learning

process must be adapted not only to the student’s

profile but to the learner’s context as well, creating

some kind of matching between context and profile

to provide for example the appropriate content, na-

vigation, and recommendations. Learning processes

have to provide extremely contextualized content

that is highly coupled with context information, li-

miting their reuse in some other context. If the con-

text information is represented independently from

content information, the possibilities for reuse in-

crease.

In a broader sense, context describes the circums-

tances under which something occurs as well as the

interrelationships of those circumstances. Such inter-

relationships provide a semantic perspective that

restricts and narrows the meaning of “something”

(Abarca et al., 2006). A context-aware ELS is an

application that adapts its behavior according to the

students’ context. Context-aware applications not

only use context information to react to a user’s re-

quest, but also take the initiative as a result of con-

text reasoning activities (Dockhorn Costa et al.,

2007). We have developed a model based on upper-

level ontology. In this model, a student might be

involved in several overlapping contexts, and conse-

quently, his/her educational activity might be influ-

enced by the interactions between these contexts.

Overlapping contexts contribute to and influence the

interactions and experiences that people have when

performing certain activities (Bouzeghoub and Do

Ngoc, 2008), (Yang et al., 2006), (Eyharabide and

Amandi, 2008). Our model has three levels: meta-

model, model (ontologies), and object (Eyharabide

et al. 2009). The meta-model level is represented by

an upper ontology; the model level with several on-

tologies to describe the elements that populate the

context and, in the lower level, we find the instantia-

tions of the context ontologies. In other words, the

ontology concepts of one level are the instantiations

of its immediate superior level.

We personalize an ELS for each user based on

the information stored in a student model. In our

work, the typical characteristics of students are ex-

tended to include the context dimensions having

personal, technological, pedagogical and cultural

aspects.

Personal context is widely considered in ELS,

usually gathered in user profiles. It considers the

student’s personal information (such as name or ad-

dress) and also the student’s personal preferences

(like interaction preferences, colors or layouts). In

our environment, typical characteristics of user pro-

files include age, scholarship, background, gender,

interests, knowledge, experiences, goals, behavior,

and navigational preferences.

Technological context is related to many differ-

ent technological constraints (e.g., device processing

power, display ability, network bandwidth, connec-

tivity options, location and time). It includes con-

cepts such as browser type and version, operating

system, IP address, devices, processing power, dis-

play ability, network bandwidth or connectivity op-

tions.

Pedagogical context consists of multifaceted

knowledge due to many distinct viewpoints of peda-

gogical information needed to personalize e-

learning. In practice, many adaptive systems take

advantage of users’ knowledge of the subject being

taught or the domain represented in the hyperspace,

and the knowledge is frequently the only user fea-

ture being modeled (Brusilovsky and Míllan, 2007).

Recently, various researches started using different

characteristics described in other related fields, such

as personality model OCEAN (Goldberg, 1993),

cognitive (Ford and Chen, 2000) and learning styles

(for example, from Felder's model (Felder and Brent,

2005).

3.1 Cultural Context

Cultural context is referred to different languages,

values, norms, gender, social or ethnic aspects or

even ideological, political and religious aspects. It

describes cultural characteristics on different levels,

such as national, organizational or individual charac-

teristics. In turn, culture can be analyzed in some

levels: national and regional aspects, organizational

aspects, professional aspects and fields, and individ-

ual aspects. There are different cultural dimensions

proposed in the literature, but the most accepted for

national point of view are the five dimensions pro-

posed by Hofstede (1991), based on value orienta-

tions and shared across cultures. According to Bos-

sard (2008) there are two categories of topics that

are affected in human computer interaction localiza-

tion, (i) presentation of information (e.g. time, date

and color format) and language (e.g. font, writing

direction, etc.); and (ii) dialog design (e.g. menu

structure and complexity, layout, positions) and inte-

raction design (e.g. navigation concept, interaction

path, interaction speed, system structure, etc.). De-

spite some HCI works now focusing on cross-

cultural aspects in HCI, the research of cultural-

TAKING RICH CONTEXT AND SITUATION IN ACCOUNT FOR IMPROVING AN ADAPTIVE E-LEARNING

SYSTEM

167

dependent aspects of HCI, is still embrionary (Za-

harias, 2008).

Cultural aspects are preferences and ways of be-

havior determined by the person’s culture. Cultural

context includes cultural background of a student

and may have a great impact on their ability and

efficiency to learn a given set of content (Chandra-

mouli et al., 2008). A Culture Profile cannot be de-

fined as a fixed or prescribed specification. The spe-

cification should be extended and dynamically im-

proved based on the user´s context. As described in

Reinecke and Bernstein, (2007), research conducted

on the effect and usability of culturally adapted web

sites and interfaces has shown enormous improve-

ments in working efficiency.

Cultural-aware in this paper deals in identify na-

vigations paths and user´s behavior in an ELS to

support adapting content and navigation. It is not our

goal to treat sociological aspects.

3.2 Modeling Context and Culture

The meta-model, presented in Figure 1, is an upper-

level ontology describing abstract concepts like user,

application, user profile, situation or date. The mod-

el depicts the different contextual dimensions. Each

contextual dimension is represented by a different

ontology such as a cultural ontology (with concepts

like nationality and values, language, etc.), educa-

tion ontology (course, learning style, discipline,

etc.), personal ontology (name, gender, preferences

as navigational mode and interface colors, birthday,

action focus in this moment, etc.) or technological

ontology (operating system, browser, network

bandwidth, etc.). Finally, the object model will com-

prise instances describing the context of a particular

user like a concrete name (John Smith), a course

(Human Computer Interaction) or a particular lan-

guage (English).

The situation could be completely changed if the

contexts of student change. Among all the possible

information gathered in the student model, we are

especially interested in modeling scenarios because

they change according to context. Scenarios may

depend on the situation the student is now in and on

external factors. The concreteness of scenarios helps

students and teachers to develop a shared under-

standing of the proposed contextual information, and

allows assimilating and representing complex idio-

syncrasies of that they would otherwise misunders-

tand.

We define a scenario as a tuple containing an

entity that the student prefers in a given situation, a

relevance denoting the student’s preference for that

Figure 1: Example of a scenario-oriented situation.

entity, a certainty representing how sure we are

about the student having that preference and a date

to indicate when that preference is stored:

Scenario = {entity, situation, relevance, certainty, date}

Situations are the key to include temporal aspects

of context in a comprehensive ontology for context

modeling, since they can be related to suitable no-

tions of time (Dockhorn Costa et al., 2006). As con-

text varies during certain time intervals, it is vital to

consider it within the concept of Situation. Examples

of situations could be “John was at home using his

notebook to read lesson number 3 of the Human

Computer Interaction course” or “A Japanese Pro-

fessor, who speaks English, is adding new exercises

to the course Introduction to Java using a high speed

connection while she travels by train”. Therefore, we

define situation as a set of contextual information in

a particular period of time:

Situation = {Context, initial time, final time}

An example of contextual information would be:

“The student named John is reading lesson number

7”. This is a description relating an entity (the stu-

dent John) to another entity (the lesson number 7)

via a property (is reading). We represent this contex-

tual information as (Student.john, isReading, Les-

son.lesson#7). We define the context as a set of

triples composed by concepts, instances and rela-

tions between them. It is important to emphasize that

the concepts and instances might belong to the same

ontology or different context ontologies:

Context = {(Ca1.Ia1, R1, Cb1.Ib1), ..., (CaN.IaN, RN,

CbN.IbN)}; (C: concept, I: instance and R: relation)

To clarify these ideas, let us consider again John

example. John prefers reading visual learning ma-

terial in a situation when he is at home using his

CSEDU 2011 - 3rd International Conference on Computer Supported Education

168

notebook to read lesson number 3 of the Human

Computer Interaction course. Hence, the correspond-

ing context1 will be:

Context1={ (Person.John, locatedIn, Location.home), (Per-

son.John, uses, Device.notebook), (Person.john, reads, Les-

son.lesson#3), (Lesson.lesson#3, belongsTo, Course.HCI)}

Situation1={ Context1, 4:00PM, 7:00PM}

Scenario1={User, Situation1, relevance.high, certainty.95%,

date.05-02-2010}

4 ARCHITECTURE FOR

CONTEXT-AWARE ELS

The extended AdaptWeb

architecture is presented

in the Figure 2, where the boxes represent the new

modules inserted in the already functioning architec-

ture of AdaptWeb

. Beyond the new modules, is

showed in the figure the three servers which were

proposed to store and model the context data.

Figure 2: Extended architecture.

Starting with the modules, the User Interface

Component is responsible to both obtain the user

data, and present the adaptations processed by the

environment. Actually, the AdaptWeb

environment

already stores all the information related with the

tions to the students. So, it is possible to aggregate

user context data to be obtained via interface, like

the learning object actually in use and the path made

by the student while using AdaptWeb

. Knowing

this path, we can discover the occurrence of learning

events that are important to starts an adaptation.

These events are detected by the Context Collec-

tor/Detector and, depending on the event, notified to

the Context Management Service.

The extended architecture is based on three serv-

ers that operate together to provide and manage con-

textualized data according to the student's scenarios.

Each server manages specific data related to the user

context, being respectively responsible for the sto-

rage and adaptation of (i) environmental context

(information related to the user environment, tasks,

activities, time interval, devices, location), (ii) in-

formation about students (personal data, preferences,

objectives, knowledge background, behavior, learn-

ing styles, cultural context, etc.), and (iii) learning

object’s information (documents provided by the

educational environment to its users for their learn-

ing).

The Context Management Service is responsible

for analyzing the context managed by the servers,

generating different scenarios that can be expe-

rienced by the students in a specific period. These

scenarios are used to guide the adaptation (in the

Adaptation Engine), and materialized in the interface

rendered to the user. The main goals of the architec-

ture are: (i) easily reuse of educational resources,

since they will be adapted to the user scenario while

the stored content remains the same, (ii) integration

into the existing architecture, since the new architec-

ture is supposed to take advantage of the existing

functionalities and (iii) extensibility to other educa-

tional systems, using standard technologies. The

personalization is possible with the combination of

contextual data related to whom and where the user

is, what he/she is doing and what does he/she needs

to achieve his/her educational targets. More details

can be found in (PERNAS et al., 2010).

5 ADOPTING CONTEXT

MODELING

In this section, we describe some improvements of

the personalization’s capabilities of AdaptWeb

order to provide support to this contextual modeling

approach. We start by describing different learning

situations to explain the contextual adaptations de-

veloped in AdaptWeb

, and then we detail how

those situations trigger the corresponding contextual

adaptation. We show some examples of possible

contexts in a Database System course.

We show some examples in a Database Systems

course context where the teacher provided a set of

links learning objects with diverse content about

database system, for example: History and motiva-

tion for database systems, Components, DBMS

functions, Database architecture and data indepen-

dence, etc. A learning object (LO) is defined as any

entity, digital or non-digital, that may be used for

learning, education or training (IEEE, 2002). For a

simplification purpose, we have a few variables over

student´s model: student's knowledge, subject, net-

TAKING RICH CONTEXT AND SITUATION IN ACCOUNT FOR IMPROVING AN ADAPTIVE E-LEARNING

SYSTEM

169

work connection, learning style, Language, Langua-

geLevel and Country.

In Context1, Mike is a student who lives in Bra-

zil, his mother tongue is Portuguese, and he has a

low level knowledge in English. He is trying to learn

about the subject XML databases, which is ex-

plained in English. He is doing exercises about that

subject, but unfortunately he is not obtaining satis-

factory results. In addition, he has a high network

connection and according to Felder’s model (Felder

and Brent, 2005) he is active.

The user model checks his number of mistakes

and identifies if he needs help resolving the exercis-

es. In the meantime, the situation model detects via

teacher’s agenda that a chat with the students was

previously scheduled by the teacher to happen in 15

minutes. These events will start a service of notifica-

tion in the Context Management Service, informing

that a change of the current scenarios related with

these events may change. After a new orchestration

by the Context Management Service, the User Inter-

face sends a message to the student, notifying him of

this possibility to solve his doubts and shows the

“chat” link in a different and highlighted color.

In another scenario, Context2, Marie, a French

speaking PhD student of Engineering from France,

has very good skills in three different foreign lan-

guages (English, Portuguese and Spanish). She is

also learning the subject XML databases and not

having good results. She has a low network connec-

tion and her Felder's learning style is reflective. In

consequence, AdaptWeb

sends a message by email

to her teacher advising to contact the student and

changes the order of the links, putting links related

to video material with low quality resolution in the

end and disabling links related to video material

with high quality resolution (those who are heavy

and difficult to see). Furthermore, AdaptWeb

de-

tects some important links for learning material writ-

ten in English and Spanish and shows this in the top

of the list.

These contexts are formalized as following:

Context1 = {

(Student.Mike, isLearning, Subject. XML databases),

(Subject. XML databases, isExplainedIn, Language.english),

(Student. Mike, hasUserKnowledge, UserKnowledge.bad),

(Student. Mike, hasConnection, NetworkConnection.high),

(Student. Mike, hasStyle, LearningStyle.active),

(Student. Mike, hasMotherTongue, Language.portuguese),

(Student. Mike, hasLanguageSkill, Language.english),

(Student. Mike, hasEnglishLanguageLevel,

LanguageLevel.low),

(Student. Mike, isCitizenOf, Country.Brazil)}

Context2 = {

(Student.Marie, isLearning, Subject. XML databases),

(Student. Marie, hasUserKnowledge, UserKnowledge.bad),

(Student. Marie, hasConnection, NetworkConnection.low),

(Student. Marie, hasStyle, LearningStyle.reflective),

(Student. Marie, hasMotherTongue, Language.french),

(Student.

Marie, hasLanguageSkill, Language.english),

(Student. Marie, hasEnglishLanguageLevel,

LanguageLevel.high),

(Student. Marie, hasLanguageSkill, Language.portuguese),

(Student. Marie, hasPortugueseLanguageLevel,

LanguageLevel.high),

(Student. Marie, hasLanguageSkill, Language.spanish),

(Student. Marie, hasSpanishLanguageLevel,

LanguageLevel.high),

(Student. Marie, isCitizenOf, Country.France)}

In summary, the adaptation mechanisms in

AdaptWeb

can be for example the following ac-

tions/recommendations:

Context1

“send notification to student only in

Portuguese” + “show highlighted links”+ recom-

mend LO and content about the same subject (same

concept in the domain ontology) in Portuguese with

a low level of difficulties; An example of this adapta-

tion is presented in figure 3, where the set of LO is

especially adapted to him.

Context2

“order links” + “hide or disable links”

+ “show highlighted links” + “recommend LO and

content about the same subject written in French,

English, Spanish or Portuguese”. An example of

this adaptation is presented in figure 4.

Figure 3: LO adapted to Mike´s situation.

Figure 4: LO adapted to Marie´s situation.

CSEDU 2011 - 3rd International Conference on Computer Supported Education

170

These contexts are used by the context manage-

ment service within logical rules in order to predict

future recommendations.

Currently, this model is being under evaluation

with real students and actual courses in AdaptWeb

environment.

6 CONCLUSIONS

The constant evolution of ELSs and the way people

communicates demands the development of new

efficient solutions to offer faster and better informa-

tion, aiming to improve their utilization and, more

ambitiously, the learning process. One meaningful

example is the need to deal with context modeling

and its relation with user modeling. In fact, context

modeling extends traditional user modeling tech-

niques, by explicitly dealing with aspects we sup-

pose to have a significant influence on the learning

process assisted by an ELS.

In this paper, we proposed to improve an ELS

taking into account a richer notion of context, guided

by scenarios, and showing how this context data can

be related in a daily application.

In this work, we look to increase even more the

capabilities of the actual systems personalization,

making use of ontologies to model the student’s con-

text in different scenarios, adapting the systems con-

tent, navigation and presentation. To show a mate-

rialization of this proposition, we extend an existent

ELS environment architecture and explain its new

operation.

Research in education has shown that environ-

ments, instructional design and learning methodolo-

gies cannot be always displayed in the same way,

and cannot be universally applied because their ef-

fect can vary from one culture to another, i.e. some

tactics may be effective in a cultural group, but not

in another. As well as other software applications,

ELSs are usually restricted to one personalization

strategy per country. However, a predefined loca-

lized personalization cannot be assigned to all

people of a nation, as some might have many cultur-

al influences and are, therefore, culturally ambi-

guous (Reinecke and Bernstein, 2008). In this way,

researchers are focusing on cultural aspects to pro-

duce learning technologies, and to understand the

dimension of a cultural background has on the

choice of underlying teaching methodologies. In our

approach, we consider culture as another contextual

dimension. Our future work includes increasing cul-

tural dimensions (national, social and personal) as

part of cultural context and for this improvement to

use different aspects as values, norms, social or eth-

nic aspects in the cultural context model.

We expect to have a more understanding of users

and a better communication with LO provided by

teacher, meaning effective learning for students in

AdaptWeb

environment. We plan to carry out more

experimental tests, with our partners in France and

Argentine, to develop a course with the same content

to a wide variety of students, belonging to different

cultures.

ACKNOWLEDGEMENTS

This work was partially supported by CNPq, Brazil,

(CT-Info/CNPq 17/2007) and by the projects Adapt-

SUR 022/07 (CAPES, Brazil) and AdContext 547-

07 (CAPES-COFECUB).

REFERENCES

Abarca, M., Alarcon, R., Barria, R., Fuller, D. 2006. Con-

text-Based e-Learning Composition and Adaptation.

OTM Workshops (2), On the Move to Meaningful In-

ternet Systems, pp. 1976-1985.

Barbosa, D. N. F., et al. 2006. Learning in a Large-Scale

Pervasive Environment. Proc. 4th IEEE Conference

on Pervasive Computing and Communications Work-

shops, (PERCOM), pp. 226-230.

Blanchard, E.G., Mizoguchi, R. 2008. Designing Cultural-

ly-Aware Tutoring Systems: Towards an Upper On-

tology of Culture. Workshop on Culturally-Aware Tu-

toring Systems (CATS), ITS 2008, pp 23-34.

Bossard, A. 2008. Ontology-Based Cultural Personaliza-

tion in Mobile Applications. Thesis, Department of In-

formatics, University of Zurich.

Bouzeghoub, A., Do Ngoc, K. 2008. A situation based

meta-data for describing pervasive learning objects. 1

International Conference on Mobile Learning , Uni-

versity of Wolverhampton, Ironbridge, UK.

Brown,E. J.; Brailsford, T. J.; Fisher, T.; Moore , A. Eva-

luating Learning Style Personalization in Adaptive

Systems: Quantitative Methods and Approaches. IEEE

Transactions on Learning Technologies, IEEE Com-

puter Society, 2009, 2, 10-22.

Brusilovsky, P., Míllan, E. 2007. User Models for Adap-

tive Hypermedia and Adaptive Educational Systems.

The Adaptive Web, 4321, 3-53.

Chandramouli, K., Stewart, C., Brailsford, T., Izquierdo,

E. 2008. CAE-L: An Ontology Modelling Cultural

Behaviour in Adaptive Education. 3

International

Workshop on Semantic Media Adaptation and Perso-

nalization, IEEE Computer Society, 183- 188.

Dockhorn Costa, P., Almeida, J., Pires, L., van Sinderen,

M. 2007. Situation Specification and Realization in

Rule-Based Context-Aware Applications. Distributed

TAKING RICH CONTEXT AND SITUATION IN ACCOUNT FOR IMPROVING AN ADAPTIVE E-LEARNING

SYSTEM

171

Applications and Interoperable Systems, 7

IFIP WG

6.1, DAIS 2007, Paphos, Cyprus, pp. 32-47.

Dockhorn Costa, P., Guizzardi, G., Almeida, J., Pires, L.,

van Sinderen, M. 2006. Situations in Conceptual

Modeling of Context. EDOCW '06: Proc. 10

IEEE

on International Enterprise Distributed Object Com-

puting Conference Workshops.

Eyharabide, V., Amandi, A. 2008. Semantic spam filtering

from personalized ontologies. JWE - Journal of Web

Engineering, Rinton Press, 7 (2), 158-176.

Eyharabide, V., Gasparini, I., Schiaffino, S.N., Pimenta,

M.S., Amandi, A. 2009. Personalized e-learning envi-

ronments: Considering students’ contexts. Education

and Technology for a Better World, IFIP Advances in

Information and Communication Technology, vol 302,

pp 48–57.

Freitas, V. de, Marçal, V. P., Gasparini, I., et al. 2002.

AdaptWeb: an Adaptive Web-based Courseware. In-

ternational Conference on Information and Communi-

cation Technologies in Education (ICTE).

Ford, N., Chen, S. Y. 2000. Individual Differences,

Hypermedia Navigation, and Learning: An Empirical

Study. Journal of Educational Multimedia and

Hypermedia, 9(4), 281-311.

Felder, R. M., Brent, R. 2005. Understanding Student

Differences. J. Engr. Education, 94 (1), 57-72.

Gasparini, Isabela, Pimenta, Marcelo S, Palazzo M. de

Oliveira, José, Kemczinski, Avanilde. 2010. Usability

in an Adaptive e-Learning Environment: Lessons from

AdaptWeb. IEEE Learning Technology Newsletter,

v.12, p.13 - 15.

Goldberg, L. R. 1993. The structure of phenotypic perso-

nality traits. American Psychologist, 48, 26-34.

Hofstede, G. 1991. Cultures and Organizations: Software

of the Mind. New York: McGraw-Gill.

IEEE. 2002. Draft Standard for Learning Object Metada-

ta. Available: http://ltsc.ieee.org/wg12/files/

LOM_1484_12_1_v1_Final_Draft.pdf

ISO 9241. 1998. Ergonomics requirements for office with

visual display terminals (VDTs).

MOBIlearn, 2003, MOBIlearn final report, viewed Janu-

ary 2007, http://www.mobilearn.org

Motz, R., Guzmán, J., Deco, C., Bender, C. 2005. Apply-

ing Ontologies to Educational Resources Retrieval

driven by Cultural Aspects, Journal of Computer

Science & Technology (JCS&T), 5 (4), pp 279 - 284.

Pernas, A M., Gasparini, I, Bouzeghoub,Al, Pimenta, M

S., Wives, L K., Palazzo M. de Oliveira, J. 2010. From

an e-Learning to an u-Learning Environment, 2

In-

ternational Conference on Computer Supported Edu-

cation (CSEDU), Valencia, Spain, vol 1.

Reinecke, K., Bernstein, A. 2008. Predicting user interface

preferences of culturally ambiguous users. CHI '08:

CHI '08 extended abstracts on Human factors in com-

puting systems, pp. 3261-3266.

Reinecke, K , Bernstein, A. 2007. Culturally Adaptive

Software: Moving Beyond Internationalization, HCI.

Reinecke, K., Reif, G., Bernstein, A.2007. Cultural User

Modeling With CUMO: An Approach to Overcome

the Personalization Bootstrapping Problem. Workshop

on Cultural Heritage on the Semantic Web, ISWC.

Sharples, M., Taylor, J., Vavoula, G. 2007. A Theory of

Learning for the Mobile Age, In R. Andrews and C.

Haythornthwaite (eds.) The Sage Handbook of E-

learning Research. London: Sage, pp. 221-47.

Sieg, A; Mobasher, B; Burke, R. 2007. Representing Con-

text in Web Search with Ontological User Profiles.

LNCS, Modeling and Using Context, v. 4635, pp 439-

452, Springer.

Souto, Maria Aparecida Martins, Verdin, Regina, Souza,

K. B., Zanella, R., Nicolao, Mariano, Madeira, Milton

J. P., Vicari, Rosa Maria, Palazzo M. de Oliveira, J.

2002. Web Adaptive Training System bases on Cogni-

tive Student Style In: IFIP World Computer Confe-

rence , Montreal, 25-30 Ago. Proceedings. p.281 -

288

Tetchueng, J. L., Garlatti, S., Laube, S. 2007. A Didactic-

based Model of Scenarios for Designing an Adaptive

and Context-Aware Learning System, Proc. of the

IEEE/WIC/ACM International Conference on Web In-

telligence, IEEE Computer Society, pp. 723-726.

Ullrich, C. 2008, Pedagogically Founded Courseware

Generation for Web-Based Learning -- An HTN-

Planning-Based Approach Implemented in PAIGOS,

September, 2008. Vol. 5260 Springer-Verlag.

Yang, S.J.H.; Huang, A.P.M.; Rick Chen; Shian-

Shyong Tseng; Yen-Shih Shen. 2006. Context Model

and Context Acquisition for Ubiquitous Content

Access in ULearning Environments, Proc. IEEE Inter-

national Conference on Sensor Networks, Ubiquitous,

and Trustworthy Computing, 2, pp. 78-83.

Zaharias, P. 2008. Cross-Cultural Differences in Percep-

tions of leaning Usability: An Empirical Investigation.

International Journal of Technology and Human Inte-

raction, 4 (3), IGI Global.

CSEDU 2011 - 3rd International Conference on Computer Supported Education

172