ePortfolio Data Utilization in LMS Learner Model

Vija Vagale

Faculty of Computing, University of Latvia, Raina boulv. 19, Riga, Latvia

Keywords: Learner Model, eLearning, ePortfolio, Lifelong Learning.

Abstract: In this article a research about ePortfolio utilization in eLearning systems is given, utilization opportunities

of the ePortfolio data for the adaptive learning system learner model initial data organization are described

to partly solve learner model initial data problem. It ensures time and work resource economy as well as

quick data acquisition comparing to lasting and tedious learner testing. The result of this work is a more

complete description of the learner that is quite important in case of the adaptive system. Learner model is

viewed in the lifelong learning context, turning more attention to the adult learning features. The article

encourages discussion about general dynamic learner model creation and utilization in the adaptive learning

system based on the research about possible ways of learner data acquisition.

1 INTRODUCTION

With the development of information technologies

new learning instruments that ensure more

qualitative learning process appear. Learning

Management Systems (LMS) are purposed to help

teacher by offering different types of learning

materials and by not attaching learner to certain

location and time. The number of researches about

adaptive e-Learning system (ALE) utilization for

providing learning process is increasing. In these

researches the system is able to recognize learner’s

needs and features, and offer necessary material to

the learner in an understandable way, which is more

appropriate for acquirement. The changes concern

also the learning object – learner. Nowadays

necessity for lifelong learning – i.e. learning during

the whole lifetime from childhood till old age

continuous or periodical – is increasing. The lifelong

learning importance also proves the Europeans

Commission program “The Lifelong Learning

Programme: education and training opportunities for

all” that has been realized from year 2007 to 2013

(The Lifelong Learning Programme, 2011).

Learning demands a lot of resources from adults:

both material and human resources, but gives back

multitudinous values as rise of self-confidence, self-

esteem, enlarges trust to associates, satisfaction with

life or ability to cope with difficulties, protects from

depression and enhances welfare. On the other hand,

learning process also has negative features. It can

cause anxiety, stress and affect human mental health.

Fear or aversion against learning can appear if

learning environment reminds individual his

previous negative experience about learning process

(Field, 2011). One solution for this problem is

adaptive learning management system (ALMS)

utilization in learning.

This article is oriented to learner data acquisition

types. In the learner role is viewed adult, his learning

specificity that is described in second section. When

acquiring new information, adults are based on their

own experience that can be collected in the

ePortfolio system. In the third section ePortfolio

concept essence and utilization opportunities in the

education and LMS are shown. Based on previous

research results in the fourth section user model data

classification and data life cycle is offered, and data

acquisition types are discussed. In the fifth section a

research of how data about learner from ePortfolio

can be imported to the LMS is described. The last

section contains conclusions.

2 SPECIFICITY OF ADULT

LEARNING

Adult education is a multidisciplinary process that is

oriented to supported and effective learning during

the whole lifetime. Its goal is to give knowledge that

would improve professional qualification and help to

consummate civic, social, moral and culture

489

Vagale V..

ePortfolio Data Utilization in LMS Learner Model.

DOI: 10.5220/0004447704890496

In Proceedings of the 15th International Conference on Enterprise Information Systems (ICEIS-2013), pages 489-496

ISBN: 978-989-8565-60-0

 2013 SCITEPRESS (Science and Technology Publications, Lda.)

attitudes and skills, and to gain success in all vital

spheres (De Goñi, 2006).

There exist numerous opinions about adult

education, which are determined by different factors,

for instance, differences between Western and

Eastern cultures. In the field of pedagogy different

education theories are considered (for example, M.

Knowles, N. Gruntvig, etc.). Nowadays adult

education is very often connected with the concept

of “andragogy”. Andragogy is science about adult

education that describes adult learning essence

(Knowles, 1980).

Based on theory of andragogy, scientific

researches (Merriam, 2001); (Cercone, 2008), and

practical operating in adult learning, it was

concluded that adult learner can be described as a

person who has the following qualities:

 the ability to take responsibility about the

process of self-education;

 the ability to move his/her own education and

operate by individual plan (self-direct learning);

 he/she possesses with an accumulated life

experience reserves that are abundant source to

continue studying;

 he/she has the necessity of learning that is tightly

connected with social role change;

 he/she is problem-centered, with the necessity to

use obtained knowledge immediately;

 he/she is motivated to learn with internal, not

external factors (“self-stimulant person”, self-

esteem, life quality);

 comprehension about what he/she needs to

know;

 learning irregularity (the system can be visited

very rarely because of work, family or other

obligations).

The adaptive system utilization for ensuring

education is connected with computer utilization that

is why an important role is played by an adult

attitude towards information technology utilization,

their computer skills and openness to learn new

technologies. There are a lot of researches that

describe adult learning problems by learning

information technologies (Candy, 2002); (Cercone,

2008). By researching adult learning features,

Kathleen Cercone has distinguished attributes

utilized in the adult education and for each of them

offered an appropriate education model by creating

„Recommendations for Online Course Development

based on Characteristics of Adult Learners”.

The most important adult learning feature is that

adult learning is based on their experience that has

been collected in different life situations

(Brookfield, 1995). Based on this adult learning

difference in the offered article the question of how

the accumulated experience of an adult that is

reflected in ePortfolio can be used to gain e-

Learning environment learner model start data is

researched.

3 ePORTFOLIO

ePortfolio usage for the improvement of learning

process is still a novelty. In this section the essence

of ePortolio is viewed, as well as obtainable benefits

of its utilization in education and examples of

ePortfolio usage with LMS.

3.1 The Essence of ePortfolio

Electronic portfolio or ePortfolio (or digital

portfolio) is a digitalized artifact (artifact can be any

piece of content) collection that contains

demonstrations, resources and achievements of a

person, group, community, organization or

institution (Lorenzo and Ittelson, 2005). This

collection contains text, electronic files, images,

multimedia, records and hyperlinks. Artifacts can be

also collected from a virtual space and represented

in wiki pages, blogspots or ePortfolio views (Bubaš

et al., 2011). Artifacts can be adapted so that they

can represent certain student uniqueness by ensuring

depiction that shows the depth of individual learning

(Barrett, 2004). EPortfolio data collection is placed

on the Internet and can be organized and managed

by the person who created that ePortfolio by

indicating access rights to the information.

(Grant, 2005) has focused on ambiguous concept

of ePortfolio utilization. ePortfolio type

classification is also dissenting. By content and

utilization ePortfolio can be divided into the

following types: student, teaching, institutional,

assessment, learning, developmental, working

ePortfolio, etc. (Lorenzo and Ittelson, 2005);

(Barrett, 2004). Each of above-mentioned types

offers evidences that show appropriate skills and

knowledge in an appropriate scope.

3.2 Benefits of ePortfolio

ePortfolio system popularity has recently increased

and it is used as an activity in many education

institutions. ePortfolio utilization has been widely

researched in the education institutions, for instance,

learning of portfolio utilization in higher education

ICEIS2013-15thInternationalConferenceonEnterpriseInformationSystems

490

(Zubizarreta, 2004). According to (Graf et al., 2012);

(Buzzetto-More, 2010), utilization of ePortfolio in

the process of education gives students the

following: the opportunity to develop organizational

skills; realize their skills, abilities and lacks;

estimate their own progress; demonstrate how skills

have developed over time; promote their own

professional choice; develop comprehension about

their own studying; improve motivation and

involvement into learning process; have effective

instrument to prove studying; create dialog with

teacher. ePortfolio contains personal information

about its owner, his competences, goals,

accomplished and planned works, achievements,

interests and values, thoughts, statements and

comments, test and exam results, about information

generation and ownership of some portfolio parts.

For ePortfolio creation envisaged programs are

divided into commercial and open source programs.

Interesting research has been made in the article

(Himpsl and Baumgartner, 2009) where the

evaluation criteria of ePortfolio system are described

and given twelve most popular system evaluations

by taking into account these system goals,

administration opportunities, offered activities,

publication opportunities and usability. This article

gives an overview about such system as: Drupal ED,

Elgg, Epsilon, Exabis, Factline, Fronter, Mahara,

Movable Type, PebblePad, Sakai, Taskstream,

Wordpress. (Sweat-Guy and Buzzetto-More, 2007)

compare such ePortfolio systems as Eportfolio,

Foliotex, Life Text, TaskStream, TK20, Trueout,

Blackboard and Open Source. In the article (Balaban

and Bubaš, 2010) an evaluation of Open source

ePortfolio system Mahara and Elgg was performed

for the benefit of Mahara.

After analyzing literature about ePortfolio

utilization in learning process it was concluded that

ePortfolio:

 ensures accessibility, portability, rises

technological skills, is learning-centered, offers

opportunity to find arguments and evidences

easier for collecting information about oneself

from different aspects (Raybourn and Regan,

2011);

 gives opportunity to describe oneself fully (both

internal and external worlds) (Graf et al., 2012);

 ePortfolio applications allows functional

integration with different Web 2.0 applications

and can be used as a contact for e-Learning

activities (Orehovački et al., 2012);

 content a little bit duplicates with data about an

individual that are stored in the social network;

in some learners it causes disinclination to use

ePortfolio system (Griesbaum and Kepp, 2010);

 is self-expression type; helps to find

collaborators to share with common interests;

ePortfolio is intersection of reflection,

documentation and mentoring (Seldin, 1997).

3.3 ePortfolio Usage with LMS Systems

When making a research about ePortfolio utilization

opportunities for learner model data acquisition, it

was concluded that in the learning process ePortfolio

is mostly used only as data storage with a purpose to

store learner data and achievement evidences

together. Only in a few articles experiments using

ePortfolio data for learner model (LM) initialization

are viewed. Further some ePortfolio usage examples

are mentioned.

ePortfolio utilization with the purpose of

reflecting and presenting student works and allow

others to estimate these works is viewed in Bubaš, et

al. article (2011) where an integration of Moodle

learning system, ePortfolio system Mahara and blog

posts system WordPress is performed.

(Griesbaum and Kepp, 2010) describe Moodle

integration with ePortfolio system Mahara CollabIni

at the University of Hildesheim. In this article

ePortfolio is used as an instrument to ensure

personal information management for all university

members with the purpose to facilitate self-

presentation opportunities.

(Knight and Bush, 2009) describe Integrated

Learning Environment (ILE) where they perform

Simulated Professional Learning Environment

system integration with LMS (Moodle) and

ePortfolio System (Mahara) with united student

registration in all systems.

(Guo and Greer, 2006) use ePortfolio artifacts for

LM initialization. Scholars choose artifacts as

evidences based on the questions asked. A system

based on ePortfolio data performs a test by searching

appropriate artifacts. At the end of course obtained

learning results can be saved in ePortfolio.

4 THE LEARNER MODEL

The basis of an adaptive system is composed of

three main components: the domain model, the

adaptive model and the learner model. The domain

model stores knowledge acquired by a learner that is

divided into small parts such as concepts. The

adaptive model ensures an appropriate system

adaptation function by adapting acquired

ePortfolioDataUtilizationinLMSLearnerModel

491

information based on learner necessities and

features. The learner model (user model or student

model) contains data that describe some real person

who is a learner in this system. The depiction of the

learner data in the system is connected with time

dimension by showing certain data values that

describe system user in certain point of time or

interval.

Based on the previous research (Vagale and

Niedrite, 2012b) about in LM found data types, ALE

learner model data by their meaning and life length

are divided into three groups: basic data, additional

data and complete data. Created division helps fully

describe the LM data life cycle.

4.1 LM Data Types and their

Acquisition

The first time when a user registers in the system, it

gains basic data about this individual that are

unchanged or static, their value during the system

utilization stays unchanged or is changing very

rarely. Basic data contain learner personal

information (login, password, name, surname, email,

gender, age, date of birth, native language,

nationality, address).

Basic data values are written in LM based on: (a)

system administration registration data; (b) user-

filled registration form; (c) user data import results

from other systems.

LM basic data are not enough for learning

system to adapt to certain learner necessities. System

also collects additional data that highlights

individual features of a learner. Additional data

characterize learner as a personality (personality

data) – his individual features, concentration

abilities, personality type, collective work abilities,

relationship formation abilities, emotional condition,

attitudes, learning style and cognitive types. The

additional data can save also information about what

a learner must acquire (pedagogical data - programs,

topics, course sequence, plan); data that describe an

adaptive environment for learning (preference data -

language, presentation format, sound value, video

speed, web design personalization); data that

describe previously obtained experience of a learner

in work with computers and software that will be

used during learning process (system experience -

obtained certificates, skills in e-Learning system

utilization) and data that characterize system user

working environment (device data - hardware,

download speed, screen resolution).

Figure 1 shows the sequence of LM data

acquisition based on data type classification that is

described in the article (Vagale and Niedrite,

2012b).

LM basic

data

LM additional

data

complete data

Personal

data

Personality

data

Preference

data

System

experience

Pedagogical

data

History

data

Device data

Student knowledge at the

current moment of

time

Learning

process

LM certain

moment data

periodicity

Figure 1: LM data acquisition sequence.

Additional data are dynamic. At the beginning of

learning, data that the system will use to ensure the

adaption are collected. But over time these data

about the person (for instance, learning style, goals,

etc.) change that is why in the adaptive system

additional data must be periodically updated. This

process is shown in Figure 1 with an interrupted

bullet from additional data to complete data.

After researching scientific articles about LM

additional data acquisition types it was concluded

that for LM additional data acquisition can be used

in the following scenarios: (a) during the process of

registration the system offers to accomplish test or

tests to acquire certain data, and a user himself can

choose which tests to accomplish; (b) during the

process of registration the system offers non-

adaptive content, registers user’s activities, then with

the help of data mining calculates data about the

learner, for example, learning styles; (c) additional

data are obtained from other systems (registration

system, other learning system, social network,

ePortfolio) after the process of user registration.

Above-mentioned scenarios are depicted in

Figure 2, where from basic data with interrupted

lines possible optional transitions to the data

acquisition types are depicted: (a) to the data

acquisition with the help of tests, (b) to the data

acquisition as the result of data processing, where

data are taken from other system or (c) LM basic

data are taken as complete data and only later by

analyzing learning results and registered user

activities with the help of data mining algorithm

additional data about an individual are gained. In

Figure 2 from additional data block goes an

interrupted bullet, which indicates that additional

data can be restored periodically.

Theoretically, the more additional data about the

user the learning system can gain, the more precise

is his depiction in this system. However, only by LM

and adaptive model mutually interaction good

system adaptation ability can be ensured.

ICEIS2013-15thInternationalConferenceonEnterpriseInformationSystems

492

Learning process

Data minin

LM additional data acquisition

LM certain moment data

refreshing

periodical event, which is

detected by the system

LM basic

data

LM additional

data

Testing

Learning

styles

... ...

...

LM complete

data

Domain

model

Adaptive model

Content conformity

table

Adapted content

LM certain

moment data

Obtained data in the

learning process

Learning results

Data

warehouse

Behavior

patterns

questionnaire

learner

teacher

learner

Transformation

key

learner

Profile

LM basic data acquisition

Processing

ePortfolio

... ...

Other

stem

Log files

LM new additional data

acquisition

Figure 2: Learner model life cycle.

LM complete data shows how the system

interprets real learner in a certain point of time.

Complete data includes all information that the

system knows about the user in a certain point of

time. Complete data includes basic data, additional

data, learner knowledge in a certain point of time

and activities done during the learning process and

results.

4.2 LM Life Cycle and Place in an

Adaptive System

ALE learner model modeling process consists of

model initialization, updating and data reasoning.

More about it is written in the article (Vagale and

Niedrite, 2012a). In the Figure 2 the most important

processes that occur in adaptive system in

connection with the learner model are shown.

Processes are depicted in boxes with intermittent

borders. The interrupted bullets show dispensable

transitions. During the learner model life cycle the

following actions occur:

1. At the beginning of LM life cycle basic data

and/or additional data about the learner are

collected. Additional data are obtained as a result

of testing or other system processing. In this step

LM initializations occurs and as a result the

system “gains” a view of the learner. At the end

of initialization LM complete data are obtained.

2. System now has information about the user and

with the help of the adaptive model offers him

acquired information in the most appropriate

way. Adaptive model takes data from LM and by

using “Content conformity table” according to

LM data offers new information in agreeable

way.

3. While learning, a learner interacts with the

system. The system saves all learner activities

and results them in data base tables or event

4. When a learner has ended up with interaction

with the system, it performs collected data

analysis and processing, for example, by using

data mining algorithms or user behavior patterns.

Then, an acquisition process of the new

additional data that are connected with learner

takes place.

5. After new data acquisition the system updates

LM by rewriting or adding new LM model data.

As a result, LM complete data are obtained that

remain actual till the next data updating time.

6. Returning to step 2.

In the case of adult learning, it is important to

anticipate LM data periodical refreshing from

ePortfolio type system. In this case conflict solving

that is connected with the age (i.e., the newest data)

and data correction (i.e., data that have higher

priority) must be anticipated.

5 DATA ACQUISITION FROM

EPORTFOLIO

One of the newest research directions in creation of

the learner model is its dynamic modeling where

student interaction with the system is continuously

supervised and LM data are updated in real time

(Graf et al., 2012). However, the question about

those human-characterized data that are already

collected in other system is still topical. In the

general case a person can use more learning system,

ePortfolioDataUtilizationinLMSLearnerModel

493

ePortfolio systems and also other environments not

connected with learning that can store user-

characterized data. Acquisition and utilization of

these data in adaptive system as LM additional data

is topical for modern researchers.

5.1 Data Integration Examples

Possible options of the data acquisition from another

system: (a) data migration – data are imported from

the other system, in the source system data are

deleted, synchronization between both systems does

not exist; (b) data integration – between both

systems data synchronization exists.

In case of data integration, some problems like

data structure, syntax and semantic heterogeneity

problems must be solved (Walsh et al., 2011). To

solve these problems, data unification or mapping

schemes are created. Mapping is a presentment of an

association between different system data model

identical data (Walsh et al., 2011).

Mapping can be fulfilled automatically by

determining conformity between appropriate

attributes with identical attribute names or manually

when conformity between system data is made by an

administrator or a system designer.

For mapping result storage general user models

or learner model server are used. (Niedritis et al.,

2011) in the article use Generic User Model for this

purpose. (Walsh et al., 2011) have described data

integration between systems Sakai and Moodle with

the help of framework FUMES, and mapping results

are stored in the user canonical model. Van Der

Sluijs and Houben (2006) use Shared User Model.

For data transferring from one system to other

mostly eXtensible Markup Language (XML) is used

with standard data protocol that is employed for web

services (Walsh et al., 2011).

OWL language is used in the newest researches

of data integration problem solving. For instance,

(Van Der Sluijs and Houben, 2006) describe the

Generic User model that is based on semantic user

model interoperability.

5.2 ePortfolio Standards

EPortfolio content can be different, that is why to

get data from ePortfolio system they should be

standardized (Guo and Greer, 2006). Standardized

ePortfolio information model describes what

information in general ePortfolio contains and what

set of specifications is defined for describing data

organization in ePortfolio. Standards that describe

information and relationships between them stored

in ePortfolio are: IEEE P1484.2.26 – Learner

Portfolio Information; JISC CETIS LEAP2A

Specification; IMS ePortfolio Specification; CELTS

Portfolio information.

Majority of researches are in favour of IMS

ePortfolio specification. IMS LIP (Learner

Information Package), IMS ePortfolio and LEAP2A

comparison is viewed in (Hämäläinen et al., 2011).

5.3 Research

LMS Moodle (Modular Object-Oriented Dynamic

Learning Environment) and the newest versions of

ePortfolio system Mahara described in the article

(Vagale and Niedrite, 2012a) were used in the

research. Both of the systems are open source

programs; their structure is based on modular

principle, and both systems are compatible with each

other. In these systems united user authentication is

possible. In Mahara system user, group, view,

system security, authentication management and

new plug-in installation is realized.

It is possible to export from Mahara the

following: user personal information, saved user

files, short records and descriptions. Mahara

supports data export in HTML and LEAP2A

formats. Unlike HTML format, LEAP2A saves more

complete information taking into account

relationships between artifacts. In Mahara system

two additional modules, which can be used for

determining learning style by Fleming’s VARK

model and intellectual abilities, were installed. For

exporting all user data including learning style and

intellectual test results were taken into account.

In Moodle system data that describes learner are

stored in data base table user. These data are

available in user’s portfolio. EPortfolio system

stores much more information about the user than

Moodle. Table 1 demonstrates data comparison,

showing what kind of data can be taken from

Moodle and Mahara for LM initialization. Colored

rows show LM data category names and white ones

show these category data. From Moodle user profile

almost all data that are necessary for LM basic data

can be obtained. These data can be gained also from

exported LEAP2A file by using records that describe

appropriate artifact type (for example, email

corresponds to <mahara:artefacttype=”email”>).

Moodle does not save LM necessary additional data.

It collects only user activities. However, exported

file can gain data from Mahara that describes learner

working experience, skills, goals, interests,

certificates and obtained educations. Personal data

acquisition is possible from an appropriate data type

ICEIS2013-15thInternationalConferenceonEnterpriseInformationSystems

494

record (for instance, personal skills correspond

<mahara:type=”personalskill”>). In ePortfolio added

plug-in results are gained after installed block type

(e.g., learning style corresponds

<mahara:blocktype="learningstyles">).

Table 1: Moodle and Mahara data conformity for LM.

Moodle

table user

LM data

category

name

Mahara

mahara:artefacttype/

mahara:type

Personal data

username login

password password

firstname name firstname

lastname surname lastname

email email emai

gender personalinformation/gender

date of birth personalinformation/dateofbirth

lang language

city city town

country country country

Personality

data

learning style blocktype="learningstyles"

intelligences blocktype="multipleintelligences"

individual

features

work

experience

employmenthistory, occupation

goals personalgoal, academicgoal,

careergoal

skills personalskill, academicskill,

workskill

interests interest

Pedagogical

data

Preference

data

System

experience

certification, academicskill

pseudo:educationhistory

Device data

+/-

History data

Current

moment’s

knowledge

academic skill

In Table 1, a “-” symbolizes the absence of

appropriate data. Near history data, a ”+/-” means

that Moodle system collected data will be useful, but

they are insufficient for an adaptive system function.

Pedagogical data that describe study program,

course topic sequence and learning plan saving in

Moodle is not foreseen. They will be described by

course teacher or adaptive system based on learner

plans and goals. Device data that describe working

environment of the learner can be determined

automatically with the help of software. Preference

data that will adapt learning system working

environment will be created by the system itself

based on collected device data and individual

features. Evidence about learner knowledge in

certain point of time at the beginning can be taken

from academic skill saved in Mahara and later be

supplemented with data that will be obtained during

the learning process.

6 CONCLUSIONS

A LM life cycle in an adaptive system and learner

model data acquisition opportunities were described

based on LM data division offered in this article. By

researching ePortfolio data utilization opportunities

for LM initialization one can conclude that it is

possible to make an automatic data selection from

the data saved in LEAP2A specification format.

Data saved in basic constructions of ePortfolio

system can be collected easier and more

qualitatively. From data exported from Mahara one

can automatically obtain basic data and additional

data that describe personality (personality data).

Qualitative additional data acquisition has an impact

on the ePortfolio system input information

completeness and precision and also the kind of

additional models used in ePortfolio system. Based

on research results one can assert that ePortfolio data

can be used for LM automatic initialization.

EPortfolio data are continuously updated and

supplemented that is why periodical data

actualization from ePortfolio system must be

foreseen in the adaptive system. It will help to

specify the LM, which is especially important in

case of adult learning.

Future work is connected with practical

realization of the learner model by using data about

learner that are available in other systems, for

instance, in ePortfolio. On the basis of the obtained

data an analysis on the subject of which adaptation

type is the most suitable for each data type.

REFERENCES

Balaban, I., & Bubaš, G. 2010. Educational potentials of

ePortfolio systems: Student evaluations of Mahara and

Elgg. In Information Technology Interfaces (ITI),

32nd International Conference on IEEE, pp. 329-336.

Barrett, H., 2004. Differentiating electronic portfolios and

online assessment management systems. In The

annual conference of the Society for Information

ePortfolioDataUtilizationinLMSLearnerModel

495

Technology in Teacher Education, vol. 2004, No. 1,

pp. 46-50.

Brookfield, S., 1995. Adult Learning: an overview.

Oxford: Pergamon.

Bubaš, G., Coric, A. & Orehovački, T., 2011. The

integration of students’ artifacts created with Web 2.0

tools into Moodle, blog, wiki,e-portfolio and Ning.

34th MIPRO International Convertion on Computers

in Education. Rijeka: Croation Society for Information

and Communication Technology, Electronics and

Microelectronics.

Buzzetto-More, N., 2010. Assessing the Efficacy and

Effectiveness of an E-Portfolio Used for Summative

Assessment. Interdisciplinary Journal of E-Learning

and Learning Objects, 6, pp. 61-85.

Candy, P.C., 2002. Lifelong learning and information

literacy. In White paper prepared for UNESCO, the

U.S. National Commission on Libraries and

Information Science, and the National Forum on

Information Literacy for use at the Information

Literacy Meeting of Experts. Prague, Czech Republic.

Cercone, K., 2008. Characteristics of adult learners with

implications for online learning design. AACE

Journal, 16(2), pp. 137-59.

De Goñi, J.I.M.M., 2006. What is adult education?

UNESCO answers. San Sebastián UNESCO Centre.

Field, J., 2011. Adult Learning, Health and Well-Being-

Changing Lives, Adult Learner. The Irish Journal of

Adult and Community Education, pp. 13-25.

Graf, S., Kinshuk, K. B., Khan, F. A., Maguire, P.,

Mahmoud, A., Rambharose, T., Shtern, V., Tortorella,

R. & Zhang, Q. 2012. Adaptivity and Personalization

in Learning Systems based on Students’

Characteristics and Context. In The 1st International

Symposium on Smart Learning Environment.

Grant, S., 2005. Clear e-portfolio definitions: A

prerequisite of interoperability. In 2005 ePortfolio

Conference. Cambridge.

Griesbaum, J., & Kepp, S. J., 2010. Facilitating

collaborative knowledge management and self-

directed learning in higher education with the help of

social software. concept and implementation of

collabuni–a social information and communication

infrastructure. In Proceedings of I-KNOW 2010, 10

International Conference on Knowledge Management

and Knowledge Technologies, pp. 415–426.

Guo, Z. & Greer, J., 2006. Electronic Portfolios as a

Means for Initializing Learner Models for Adaptive

Tutorials. In Innovative Approaches for Learning and

Knowledge Sharing. Berlin/Heidelberg, Springer.

Hämäläinen, H., Ikonen, J. & Nokelainen, I., 2011. The

Status of Interoperability in E-Portfolios: Case

Mahara. In 7th E-learning Conference, e-Learning'11

(E-Learning and the Knowledge Society). Bucharest,

Romania, pp. 64-69.

Himpsl, K. & Baumgartner, P., 2009. Evaluation of e-

Portfolio Software. International Journal of Emerging

Technologies in Learning 2009, 4(1), pp. 16-22.

Knight, A. & Bush, F., 2009. The development of an

integrated learning environment. In ascilite Auckland.

Knowles, M., 1980. The Modern Practice of Adult

Education. In Pedagogy to Androgogy. Chicago, pp.

263-264.

Lorenzo, G. & Ittelson, J., 2005. An overview of e-

portfolios. EduCause Learning Initiative Paper, 1.

Merriam, S.B., 2001. Andragogy and Self-Directed

Learning:Pillars of Adult Learning Theory. New

Directions for Adult and Continuing Education, 89,

pp. 3-13.

Niedritis, A., Niedrite, L, Kozmina, N., 2011. Integration

Architecture of User Models. Perspectives in Business

Informatics Research, Local Proceedings, BIR 2011,

Latvia Riga, pp. 323-330.

Orehovački, T., Bubaš, G., Kovačić, A., 2012. Taxonomy

of Web 2.0 applications with educational potential. In:

Transformation in Teaching: Social Media Strategies

in Higher Education. Informing Science Institute,

Santa Rosa, pp. 43–72.

Raybourn, E., & Regan, D., 2011. Exploring e-portfolios

and Independent Open Learner Models: Toward Army

Learning Concept 2015. In The Interservice/Industry

Training, Simulation & Education Conference

(I/ITSEC) (Vol. 2011, No. -1). National Training

Systems Association.

Seldin, P., 1997. The teaching portfolio: A practical guide

to improved performance and promotion/tenure

decisions, 2nd ed. Boston: Anker.

Van Der Sluijs, K & Houben, GJ. 2006. A generic

component for exchanging user models between web-

based systems, International Journal of Continuing

Engineering Education and Life Long Learning, vol.

16, no. 1, pp. 64-76.

Sweat-Guy, R. & Buzzetto-More, N., 2007. A

comparative analysis of common e-portfolio platforms

and available features. Issues in Informing Science and

Information Technology Education, 5(1), pp. 327-42.

The Lifelong Learning Programme: education and training

opportunities for all, 2011. Available from:

<http://ec.europa.eu/education/lifelong-learning-

programme/doc78_en.htm > [30 March 2013].

Vagale, V. & Niedrite, L., 2012a. Intellectual Ability Data

Obtaining and Processing for E-learning System

Adaptation. In Workshops on Business Informatics

Research. Springer Berlin Heidelberg, pp. 117-1.

Vagale, V. & Niedrite, L., 2012b. Learner Model’s

Utilization in the e-Learning Environments. In

Databases and Information Systems, DB&IS 2012.

Lithuania Vilnius:Žara, pp. 162-174.

Walsh, E., O'Connor, A. & Wade, V., 2011. Supporting

Learner Model Exchange in Educational Web

Systems. In 7th International Conference on Web

Information Systems and Technologies.

Noordwijkerhout, The Netherlands.

Zubizarreta, J., 2004. Reflective practice for improving

student learning. In The learning portfolio. Bolton,

MA: Anker.

ICEIS2013-15thInternationalConferenceonEnterpriseInformationSystems

496