Conference PaperPDF Available

A generic solution approach for integrating adaptivity into web-based e-learning platforms

Authors:

Abstract and Figures

Adaptation is a well known concept in the field of e-learning and is increasingly applied in modern learning systems. In order to gain more flexibility and to enhance existing e-learning platforms, we have developed a generic solution approach which enables to add adaptation functionality to existing Web-based e-learning systems. In this paper we present a distributed architecture on the basis of Web services, which is based on experiences gained in the AdeLE and iClass research projects. This flexible solution allows for adapting towards various devices, such as PCs and handhelds. The first running prototype implements the formal Competence-based Knowledge Space Theory for effective assessment of pre-knowledge and knowledge acquisition as well as for determining the sequence of learning content.
Content may be subject to copyright.
Conference IMCL2007 April 18 -20, 2007 Amman, Jordan
1(9)
A Generic Solution Approach for Integrating Adaptivity into
Web-based E-Learning Platforms
Alexander Nussbaumer1, Christian Gütl2, Cord Hockemeyer1
1Department of Psychology, University of Graz, Austria
2Institute for Information Systems and New Media, Graz University of Technology, Austria
Key words: Adaptive E-Learning, E-Learning Platform, Knowledge Space
Theory, Web Service, Assessment, Personalised Learning Path, AdeLE, iClass
Abstract:
Adaptation is a well known concept in the field of e-learning and is increasingly
applied in modern learning systems. In order to gain more flexibility and to enhance
existing e-learning platforms, we have developed a generic solution approach which
enables to add adaptation functionality to existing Web-based e-learning systems. In
this paper we present a distributed architecture on the basis of Web services, which is
based on experiences gained in the AdeLE and iClass research projects. This flexible
solution allows for adapting towards various devices, such as PCs and handhelds. The
first running prototype implements the formal Competence-based Knowledge Space
Theory for effective assessment of pre-knowledge and knowledge acquisition as well
as for determining the sequence of learning content.
1 Introduction
The concept of adaptation has been increasingly addressed in the literature [1], [4] over the
last two decades. In an early paper about adaptive hypermedia Brusilovsky [1] gives an
overview about methods and possible application fields. One of the most important and
interesting one is the educational application domain. Since there are great differences with
respect to the learners' knowledge states and preferred learning styles, adaptive learning
systems can support the learning process by adapting to such parameters and characteristics.
This might be one of the most important system behaviours of an adaptive e-learning system.
There are several methods published in literature and implemented in existing systems which
can be applied to adapt the content towards the users’ needs, known as “personalisation”.
Educational adaptive systems usually work with user models, which contain personal data
about the learner, and a domain model, which provides meta-information about the content.
Furthermore, adaptation procedures fulfil the task of adapting the presented content to the
user. Traditionally, these components are integrated monolithically in a learning system
together with all other features. This paper provides a detailed description about implementing
adaptation concepts in learning systems.
Two problems arise from a seamless integration into one system. First, an absence of
encapsulation makes it hard to change the models and procedures without changing the other
components. Second, applying adaptation functionality of one system to another system needs
much re-implementation because of the lack of reusability. To overcome these problems a
system architecture is needed, which separates models and procedures in a way that specific
Nussbaumer, A., Gütl, C., & Hockemeyer, C. (2007). A Generic Solution Approach for
Integrating Adaptivity into Web-based E-Learning Platforms. Proceedings of the
International Conference on Interactive Mobile and Computer Aided Learning (IMCL
2007), 18-20 April 2007, Amman, Jordan.
Conference IMCL2007 April 18 -20, 2007 Amman, Jordan
2(9)
adaptation functionality is independent from the rest of the system. Therefore, a more modular
system design is needed.
This paper presents an approach which postulates a system design with an encapsulated
adaptation system in an own web service. This service can be connected to arbitrary e-
learning platforms through a generic adaptation control interface. This solution has several
advantages. Existing e-learning platforms can be enriched with adaptation functionality
without changing its implementation. The separation of the adaptation functionality creates
flexibility and reusability; different learning platforms can use the same adaptation methods.
The web service approach enables the creation of the adaptation functionality as a business
model, which can be offered to learning platform operators.
Since the described solution approach refers to the server-side part of a learning system, it can
also be applied to mobile learning frameworks. Reusable adaptation functionality is also a
relevant feature for distant mobile learning.
2 State of the art
There are already systems which encapsulate adaptation by using a distributed and service-
oriented system architecture. This section discusses the two research projects AdeLE [5] and
iClass [7], whereby in both projects one of the authors is involved. They build the basis for a
more generalised design of adaptation control, which will be described in the next section.
The AdeLE software design builds on a service-based component model with a particular
component for adaptation functionality - the adaptive system - and a LMS. To connect the
adaptive system with the LMS, an adaptation control interface has been developed, which is
based on a product factory design pattern of adaptors for sequencing, aggregation, and
representing. In AdeLE a generalisation of the adaptation control interface could be realised
by an abstract design pattern, which must be implemented and applied on concrete systems.
However, this approach has its limitations, because the adaptors have to be implemented for
and inside each new system.
The iClass design [10] builds on a service-oriented architecture (SOA), where the various
personalisation functionalities are realised as Web services. For example, Monitor and
Profiler services model the learner information and Selector and LO Generator services are
responsible for delivering personalised learning path and content. Adaptation is achieved
though a coordinated system behaviour of the several services. The communication between
these services is realised by a tailored interface design.
There are further systems which have chosen a more or less modular system design in order to
encapsulate adaptation functionality. For example, APeLS [2][3][9] is a modular system
which builds upon a multi-modal approach. It comprises three models, the learner model, the
content model, and the narrative model.
3 Flexible Approach
The combination of both generalisation approaches leads to a flexible approach, which is the
central part of this paper. The main idea of this approach is to encapsulate the adaptation
functionality in a separate Web service. Then it can be connected to an arbitrary LMS with
Conference IMCL2007 April 18 -20, 2007 Amman, Jordan
3(9)
little or no adaptation ability in order to enrich it with adaptation functionality. The user
connects with the browser to the LMS and needs no extra information about the Web service.
3.1 Adaptation and Personalisation
Before specifying the system architecture and interface, it must be specified which tasks and
requirements should be accomplished with this approach. The main goal is to form a
framework for adapting the knowledge and competence state and the preferences of a learner
to the course and assessment sequence. Since the system behaviour adapts to a person, this
kind of adaptation is also called personalisation.
Input of the adaptation process is the knowledge and competence state of a learner as well as
the learner’s preferences and profile. Knowledge and competence state must be determined by
the system using assessment or monitoring the learner’s behaviour. Usually adaptation models
include procedures therefore. Preferences and profiles of learners must be manually input.
Output of the adaptation is a sequence of content objects personalised to a learner. It depends
on the particular adaptation model, which adaptation input data are processed and how they
are used for the personalisation. In any case the content is sequenced and structured by the
adaptation system, for example the order of learning or assessment objects is created
dynamically.
3.2 System Architecture
In order to accomplish this flexible approach, we propose a distributed system architecture
which consists of three components (see Figure 1): A browser, a learning management system
(LMS), and an adaptation Web service (AWS). The browser - Web browser on a computer or
a WAP browser on a mobile device - is the user interface which displays content and interacts
with the user. It is connected over the internet (cable or wireless) to the learning management
system.
The learning management system features the typical e-learning functionality, such as storing
learning content and user data, as well as providing administration and authoring tools. There
is a variety of different learning management systems, also depending on the browser type
(desktop computer or mobile device). Though they can be integrated in the system and
connected to the AWS in the same way, in order to be enriched with adaptation functionality.
Therefore an extension of the LMS is necessary which acts as a bridge between the LMS and
AWS. This extension has a defined interface to the AWS, but it must be tailored to the
individual LMS.
The Web service is the component which has implemented the adaptation model. In order to
accomplish adaptation this service needs to get information from the LMS and to control the
LMS. Since the connection is established to the LMS extension different types of LMS can be
connected to the Web service. Furthermore multiple LMS can be connected at once. The
communication between LMS and AWS is done over SOAP (originally Simple Object Access
Protocol) which provides a basic layer for exchanging messages over computer networks. In
this way browser, LMS, and AWS can be implemented in different programming languages
and running on different hosts with different operating systems.
Conference IMCL2007 April 18 -20, 2007 Amman, Jordan
4(9)
Extension
Adaptation
Web Service
(AWS)
Core
System
Extension
Internet
Internet
SOAP
SOAP
HTTP
WAP
Core
System
LMS
LMS
Desktop
Web
Browser
Mobile
Device
WAP
Browser
....
Figure 1: System architecture. The diagram shows the main components of
the system architecture, which includes browser, the learning management
system (LMS), and the adaptation Web service (AWS).
Before describing the interface between LMS and AWS, it is necessary to outline which
modules and models are comprised by which of the two components (see Figure 2). Some of
the modules and models needed for an adaptive e-learning system are described in the last
section. In this approach the responsibility of the LMS is to deal with content and user data
with respect to authoring, editing, and displaying. They are accessible to learners and
administrators (content creator and teacher). This is also the typical functionality of existing
learning management systems. Therefore the LMS needs to have repositories to store learning
objects (for example HTML pages or SCORM packages), learning information (for example
IMS LIP or PAPI), and content meta-data (for example LOM).
The adaptation system is responsible for the adaptation process. Its implementation depends
on the particular adaptation model, however it typically consists of an adaptation engine and
data models describing content, learners, and narratives. The data models refer to data in the
LMS and contain additional information, such as relations between learning objects, relations
between learning objects, learners, and competences, or knowledge and competence states of
learners. The adaptation engine is supposed to process these data in order to generate
personalised learning paths. Though this is a typical principle adaptation system, this
approach is also open for different adaptation models.
Conference IMCL2007 April 18 -20, 2007 Amman, Jordan
5(9)
Core System
Extension
Adaptation Web Service
(AWS)
Adaptation Control
Interface
Tailored Integration
Repositories
(Content, User
Narrative, ...)
Learning Management System
(LMS)
Data Models
(Content, User,
Narrative, ...)
Adaptation
Engine
Repository
Meta-data
Adaptation System
Figure 2: This diagram outlines the models and modules, as well as the interface
between the learning management system (LMS) and the adaptation Web
service (AWS).
3.3 Adaptation Control Interface
A main concern of this approach is the interface design between the LMS and AWS. Since in
this flexible design these two components are envisaged to be arbitrary, the design of this
interface is important, because it is the persistent part. However, at the technical level it
cannot be designed fully precisely, in order to keep it open for a wide range of learning
management and adaptation systems.
There are several requirements for the interface design to ensure that adaptation can be
applied on the LMS. Exchanging information about users and content between the
components must be guaranteed, as well as initiating system behaviour by sending control
commands. In detail the interface design must comprise the following parts:
1. Transferring learning and content information to AWS:
In particular existing information about registered users (learners) and about content
(learning objects) must be transferred to the adaptation system, because content should be
adapted to the learner. There are e-learning standards for these data which are suggested to
be used. For example, the Learner Information Package (LIP) and the Public and Private
Information for Learners (PAPI Learner) standard can be used to describe the learner and
the Learning Object Meta-data (LOM) standard can be used to describe learning objects.
Authoring of these data is usually provided by learning management systems.
2. Transferring specific adaptation information to AWS:
Usually adaptation systems need additional information which is not available in ordinary
learning management systems, for example relations between learning objects, skills and
skill assignments to learning objects, and didactical information. Information of this kind
can be modelled as ontologies and, for example, described with the Web Ontology
Language (OWL). An authoring tool is needed on the side of the LMS, which provides
input facility for these data. Since the LMS should not be modified, this authoring tool
should be implemented in the LMS extension module.
3. Transferring lesson and course information to AWS:
A lesson or course is a set of learning objects (or assessment objects). The information
Conference IMCL2007 April 18 -20, 2007 Amman, Jordan
6(9)
which objects are part of the lesson has to be sent to the AWS. This can be done by using
the Resource Description Language (RDF) or the Web Ontology Language (OWL). The
sequence of the objects within a lesson is determined by the adaptation system.
4. Transferring control commands to AWS:
Since the user interface is under the responsibility of the LMS, the user control commands
(for example start course, stop course, get next learning object) are input in the LMS.
Therefore they have to be sent to the AWS in order to initiate adaptation procedures.
5. Transferring sequence information to LMS:
In order to adapt content to learner (controlling the adaptation of the learning experience),
the adaptation system decides the sequence of learning objects (including assessment
objects for adaptive testing). The information which object is next has to be transferred to
the LMS after a respective user control command was received from the LMS.
3.4 Use Cases
There are four use cases which are typical for e-learning systems: system administration,
content authoring, creation of courses and lessons, and learning experience. System
administration is related to the particular LMS and adaptation system and includes tasks such
as software maintenance, user and user role administration, and setting user permissions.
Content authoring consists of two parts. First, creating and editing learning content stored in
the LMS is performed by using the genuine tools of the LMS. Second, authoring specific
adaptation information (see Section 3.3) in order to enrich learning content with additional
information needed for the adaptation process is performed by using an authoring feature
which must be provided by the LMS extension.
Creating lessons is accomplished by selecting learning objects and putting them together to a
lesson or course. Since the sequence of a lesson is determined by the adaptation system, this is
not the task of the lesson author. This functionality has to be provided by the LMS extension,
because it is different from ordinary LMS.
The learning experience of the learner is done by connecting to the LMS and choosing a
lesson. Before starting a lesson, personal profile and preferences information must be input by
the learner. The system can personalise the content to the learner and offers learning objects
fitting to the learners knowledge and competence state as well as to the learners profile and
preferences.
4 Application Prototype
An application prototype has implemented the flexible approach described above (see Figure
3). The adaptation system is founded on the Competence-based Knowledge Space Theory
(CbKST) [6], a formal psychological theory which models a learner’s knowledge and
competence state. This theory provides methods to assess the learner's competence and
knowledge state and to create a personalised learning path adapted to the learners' knowledge
level.
Conference IMCL2007 April 18 -20, 2007 Amman, Jordan
7(9)
For this prototype Moodle [8] has been chosen to act as learning management system. Moodle
is a popular open source Web application which provides an open architecture for integrating
new modules. Therefore the extension which is the bridge to the Web service can easily be
plugged to the core system. Moodle has a proven and mature user interface, which is a benefit
for learners, content creators, and lesson authors.
The adaptation system integrated into the Web service is built on the formal framework
CbKST. Algorithms and methods built on CbKST are implemented to perform content
structuring, to assess learners' competence and knowledge levels, and to create learning paths.
Utilising competence levels of learners personalised learning paths can be created by the
adaptation system.
Goal of this prototype is to demonstrate the research work done for the EC-funded iClass [7]
project. Within this project theoretical foundation of structuring content, assessing learners'
competence and knowledge levels, and creating learning paths are researched. Though they
will be implemented in the iClass system by project partners, in this prototype their
applicability can demonstrated and evaluated independent from the iClass system. The work
for this prototype is still in progress and it is planned to be published by end of 2007.
Core System
Extension
CbKST
Web Service
Learner / Teacher
Web Browser
Adaptation
Control
Interface User
Information
Domain
Ontology
Assessment
Module
Couse Creation
Module
Tailored Integration
User
Access
User Data
Learning
Objects
(incl. Test
Objects)
Moodle
Authoring
Figure 3: Prototype Application. This diagram outlines an application which has
implemented the flexible adaptation approach.
5 Conclusion and Outlook
In this paper an attempt were made to find an approach to integrate adaptivity to arbitrary
learning management systems which usually have little or no adaptivity functionality.
Adaptivity is encapsulated in a Web service which is connected to the LMS and which
controls the adaptation of the course sequence to learners. An application prototype which is
currently developed was presented to demonstrate the applicability of this approach.
Didactical models are not included in this approach at present. The next step in further
development of this approach could be to integrate adaptation to didactical models. If a
Conference IMCL2007 April 18 -20, 2007 Amman, Jordan
8(9)
teacher chooses or creates a didactical model for a lesson, then the adaptation system could
include this information when creating the sequence of the learning objects.
Further considerations can be made about monitoring the learner’s behaviour and actions in
order to exploit these data for the adaptation process. However, this might be difficult,
because it could be needed to modify the core LMS to achieve the behavioural data. On the
other hand, if an adaptation system can process these data, the degree of adaptation would be
increased.
Acknowledgements:
The work presented in this paper is partially supported by European Community under the
Information Society Technologies (IST) program of the 6th FP for RTD - project iClass
contract IST-507922. The authors are solely responsible for the content of this paper. It does
not represent the opinion of the European Community, and the European Community is not
responsible for any use that might be made of data appearing therein.
Parts of this paper are based on experiences gained in the AdeLE project. This project is
partially funded by the Austrian ministries BMVIT and BMBWK, through the FHplus
impulse program. The support of the Department of Information Design, Graz University of
Applied Sciences (FH JOANNEUM) and Institute for Information Systems and Computer
Media (IICM), Faculty of Computer Science at Graz University of Technology as well as
individuals involved in the AdeLE project are gratefully acknowledged.
References:
[1] Brusilovsky, P. (1996). Methods and techniques of adaptive hypermedia. Journal on User
Modeling and User-Adapted Interaction, 6, 87-129.
[2] Conlan, O., Hockemeyer, C., Wade, V., & Albert, D. (2002). Metadata driven approaches to
facilitate adaptivity in personalized eLearning systems. Journal of Information and Systems in
Education, 1, 38-44.
[3] Conlan, O., Hockemeyer, C., Wade, V., Albert, D., Gargan, M. (2002). An Architecture for
Integrating Adaptive Hypermedia Service with Open Learning Environments. World Conference on
Educational Multimedia, Hypermedia & Telecommunications (ED-MEDIA’02).
[4] De Bra, P., Brusilovsky, P., and Houben, G. (1999). Adaptive hypermedia: from systems to
framework. ACM Computing Surveys, 31.
[5] Gütl, C., Barrios, V., Mödritscher, F., (2004). Adaptation in e-learning environments through the
service-based framework and its application for AdeLE. In Proceedings of the ELEARN 2004,
Washington, USA (pp. 1891–1898).
[6] Hockemeyer, C., Conlan, O., Wade, V., & Albert, D. (2003). Applying competence prerequisite
structures for eLearning and skill management. Journal of Universal Computer Science, 9, 1428-
1436.
[7] iClass. http://www.iclass.info/
[8] Moodle. http://www.moodle.org/
[9] O'Connor, A., Wade, V., Conlan, O. (2004). Context-Informed Adaptive Hypermedia. In:
Proceedings of the Sixth International Conference on Ubiquitous Computing (Ubicomp'04).
[10] rker, A., Görgün, I., Conlan, O. (2006). The Challenge of Content Creation to Facilitate
Personalized E-Learning Experiences. International Journal on E-Learning (IJeL), Special Issue:
Learning Objects in Context, Volume 5, Issue 1, pp. 11-17
Conference IMCL2007 April 18 -20, 2007 Amman, Jordan
9(9)
Authors
Alexander Nussbaumer, Dipl.-Ing.
Cognitive Science Section, Department of Psychology, University of Graz, Austria
Universitätsplatz 2 / III, A-8010 Graz, Austria
alexander.nussbaumer@uni-graz.at
Christian Gütl, Dipl.-Ing. Dr. techn.
Institute for Information Systems and New Media, Graz University of Technology, Austria
Inffeldgasse 16c, A-8010 Graz, Austria, Europe
cguetl@iicm.edu
Cord Hockemeyer, Dipl.-Inform.
Cognitive Science Section, Department of Psychology, University of Graz, Austria
Universitätsplatz 2 / III, A-8010 Graz, Austria, Europe
cord.hockemeyer@uni-graz.at
... The most important are the storage layer and related reasoning layer. Adaptive systems usually work with user models containing personal data, and a domain model providing meta-information about the content [5]. In our model, we represent the domain by multiple lightweight ontologies. ...
... This personalisation approach grounds on two learning theories, Competence-based Knowledge Space Theory (CbKST) [3] and Self-Regulated Learning (SRL) [7], that are used as the underlying models for our technical implementation. Following the ideas described in [5] and [6] we have designed, implemented and integrated an adaptive learning solution in Moodle. ...
Conference Paper
Full-text available
Adaptive learning systems aim to address a learner's specific needs, considering factors such as prior knowledge, learning efficiency, learning goals and motivation. Especially in distance education, often directed to adult learners with full-time jobs, it is very important to provide assistance to counteract high dropout rates. This paper describes an approach on how to support adult learners through the adoption of personalisation and guidance in Moodle. The implementation grounds on the combination of two pedagogical theories, competence-based learning and Self-Regulated Learning (SRL). Three-phases were used to roughly frame the design of the SRL learning flow, where the individual phases are supported by competence-based guidance. In this way Moodle is extended from a teacher and course management to a learner-centric system. This work has been implemented and evaluated in the course of a European project that targets vocational training of heat pump installers.
... This personalisation approach grounds on two learning theories, Competence-based Knowledge Space Theory (CbKST) [3] and Self-Regulated Learning (SRL) [7], that are used as the underlying models for our technical implementation. Following the ideas described in [5] and [6] we have designed, implemented and integrated an adaptive learning solution in Moodle. ...
Conference Paper
Full-text available
Adaptive learning systems aim to address a learner's specific needs, considering factors such as prior knowledge, learning efficiency, learning goals and motivation. Especially in distance education, often directed to adult learners with full-time jobs, it is very important to provide assistance to counteract high dropout rates. This paper describes an approach on how to support adult learners through the adoption of personalisation and guidance in Moodle. The implementation grounds on the combination of two pedagogical theories, competence-based learning and Self-Regulated Learning (SRL). Three-phases were used to roughly frame the design of the SRL learning flow, where the individual phases are supported by competence-based guidance. In this way Moodle is extended from a teacher and course management to a learner-centric system. This work has been implemented and evaluated in the course of a European project that targets vocational training of heat pump installers.
... The CbKST service, which is based on the theory described above, provides a software for formative assessment methods that can be integrated into learning activity sequences [39]. It has been applied, for example, to enable competence assessment in a web-based system for medical training [40], and also in the scope of the NEXT-TELL [41] and the ROLE [42] projects. ...
Article
Full-text available
Service-Oriented Architecture (SOA) is a set of practices for architectural design of software that exploits services as loosely coupled components orchestrated to deliver various functionalities. The SOA paradigm is not well established in the Serious Games (SG) domain, but it is expected to provide benefits, particularly in reducing the conceptual and technological complexity of the development. In this paper, we propose and study the application of a SOA approach to SG development. We have used the SOA approach to develop an adaptive serious game for teaching basic elements of probability to high school and entry-level university students, called The Journey. Details of the architecture implementation are offered, as well as the results of an evaluation of the system using the Architecture Tradeoff Analysis Method (ATAM). Based on our experience, we argue that the SOA approach can make SG development shorter, more flexible and more focused.
Article
Full-text available
In recent years, various recommendation algorithms have been proposed to support learners in technology-enhanced learning environments. Such algorithms have proven to be quite effective in big-data learning settings (massive open online courses), yet successful applications in other informal and formal learning settings are rare. Common challenges include data sparsity, the lack of sufficiently flexible learner and domain models, and the difficulty of including pedagogical goals into recommendation strategies. Computational models of human cognition and learning are, in principle, well positioned to help meet these challenges, yet the effectiveness of cognitive models in educational recommender systems remains poorly understood to this date. This thesis contributes to this strand of research by investigating i) two cognitive learner models (CbKST and SUSTAIN) for resource recommendations that qualify for sparse user data by following theory-driven top down approaches, and ii) two tag recommendation strategies based on models of human cognition (BLL and MINERVA2) that support the creation of learning content meta-data. The results of four online and offline experiments in different learning contexts indicate that a recommendation approach based on the CbKST, a well-founded structural model of knowledge representation, can improve the users? perceived learning experience in formal learning settings. In informal settings, SUSTAIN, a human category learning model, is shown to succeed in representing dynamic, interest based learning interactions and to improve Collaborative Filtering for resource recommendations. The investigation of the two proposed tag recommender strategies underlined their ability to generate accurate suggestions (BLL) and in collaborative settings, their potential to promote the development of shared vocabulary (MINERVA2). This thesis shows that the application of computational models of human cognition holds promise for the design of recommender mechanisms and, at the same time, for gaining a deeper understanding of interaction dynamics in virtual learning systems.
Article
Full-text available
Many studies have been conducted, mainly in a university environment, and researchers have identified both advantages and disadvantages of e-learning. Very little is known about the applicability and suitability of e-learning to vocational and skills-based training. The research presented in this paper evaluates an adaptive e-learning model INNOVRET which combines skills-based learning by means of the Competence based Knowledge Space Theory CbKST with the principles of self-regulated learning SRL for a practically-oriented vocational training area, namely highly skilled heat pump system installation, in Ireland. The research methodology employed to carry out this study consists of a participative study to develop the INNOVRET approach for e-learning for heat pump systems installation and an empirical study carried out to evaluate the INNOVRET system. The results show that it is the IT skills of the installers that determine the way they perceive the system and the whole learning experience, as well as the level of knowledge acquired.
Article
Full-text available
Nowadays, the web is a widely used source of information. Therefore, current research is focusing on making the information retrieval more effective. Adaptive web technologies enable the storage of information about users and adapt the content of documents to user preferences. In our research, we are developing a general model of adaptive system. For evaluation of our theoretical results we have developed a prototype of an adaptive system and performed several experiments. In this paper we will describe important characteristics of the prototype system architecture, relations with our adaptive system model, performed experiments and proposals for future extensions.
Article
Adaptation is often a discussed topic in the field of web technologies. There is a need to personalize the information presented to the user. One of the primary problems is how to store the content within the system. The information should be understandable not only to the users who use the system, but also to the computers which prepare the data for the users. This can be achieved through the use of semantic web technologies. We propose a model for adaptive systems based on semantic representation and ontologies. We will describe the architecture of our general metamodel for adaptive systems and also our simple implementation of an e-learning system, which will be continuously extended to verify our research. We aim to create a formal description of a model, which will enable interchange of data, reuse of information and personalized search.
Article
Full-text available
The runtime creation of pedagogically coherent learning content for an individual learner's needs and preferences is a considerable challenge. By selecting and combining appropriate learning assets into a new learning object such needs and preferences may be accounted for. However, to assure coherence, these objects should be consumed within pedagogically meaningful learning activity structures. There are a number of key aspects that need to be addressed in order to perform this kind of personalization, such as the appropriate modelling of the learner's needs and preferences, representation of pedagogical strategies, representation of learning designs and assets as well as the runtime reconciliation of these elements to produce effective and coherent learning activities. Moreover, preferences that teachers may have about the learner's studies should also be considered. iClass, an Integrated Project, funded by the European Commission under the auspices of the Information Society Technologies (IST) FP6, addresses this challenge with an innovative and ambitious suite of eLearning services. This article introduces iClass and its objectives.
Article
Full-text available
Personalized eLearning Systems tailor the learning experience to characteristics of individual learners. These tailored course offerings are often comprised of discrete electronic learning resources, such as text snippets, interactive animations, diagrams, and videos. An extension of standard metadata schemas developed for facilitating the discovery and reuse of such adaptive learning resources can also be utilized by the eLearning systems for realizing the adaptivity. An important feature of such reuse supporting adaptive systems is the clear distinction of separate models and components within the teaching process.
Article
Full-text available
Adaptive Hypermedia Systems have mechanisms for extensively modelling their domain of expertise, and reasoning over that domain to produce tailored web content. In general, these systems are supplied in advance with deep, explicit models of the relevant axes of adaptivity. Current designs in Adaptive Hypermedia therefore attempt to model the entire sphere of experience of the system deeply and without separation. Contextual input, on the other hand, is arbitrarily defined, and deep models are not separated from 'shallow interest' contextual data. It is desirable to model this data separately so as to reduce the size of AH models and to encapsulate low-level sensor data as high-level interpreted concepts. This paper presents a novel method for applying contextual information to an Adaptive Hypermedia eLearning system, providing a clear boundary between 'core' adaptive axes and contextual information. An outline of the architecture of an integrated Context Interpretation system with an Adaptive Hypermedia System is provided, along with analysis of the mechanisms by which contextual information may be applied to the specific case of eLearning, and in more general systems.
Article
Full-text available
Adaptive Hypermedia Systems are capable of delivering personalized learning content to learners across the WWW. Learning Environments provide interfaces and support services to aid tutors in course construction and aid learners in navigating those courses. However, most Learning Environments deliver content sourced from local repositories. This content tends not to offer adaptive features that Adaptive Hypermedia Systems are capable of delivering. Adaptive Hypermedia Systems, which are generally Web-based, could be viewed as personalized content services, with the capacity to deliver content to many Learning Environments. However, in order to co-ordinate the correct cooperation of the Adaptive Hypermedia Service and the Learning Environment knowledge and information models need to be exchanged, e.g. learner profile, assessment information, pedagogical constraints. There does not exist, however, a standardized mechanism for integrating Adaptive Hypermedia Services with Learning Environments. In this paper the requirements for the generic integration of Adaptive Hypermedia Services with Open Learning Environments is explored. The main aim of such integration should be to work within a framework that allows for minimal impact on current Adaptive Hypermedia Services and Learning Environment implementations, while allowing for maximum standards-based interworking. This paper proposes and architecture and interface to support the collaboration of Adaptive Hypermedia Service and Learning Environments.
Article
Full-text available
E-learning may provide a lot of useful features in a wide range of learning and teaching situations. However, the provision of static learning material will not meet the requirements of the users. We believe that well-tailored, highly personalized learning sessions are needed. Regarding to this background, the research project AdeLE (Adaptive e-Learning with Eye-Tracking) aims to develop and implement a solution framework for personalised adaptive e-learning based on real-time user behaviour. In this paper we introduce the Service-Based Framework (SBF) -a reusable, scalable and flexible architecture for adaptation systems -and point out its application for AdeLE.
Article
Full-text available
Adaptive hypermedia is a new direction of research within the area of adaptive and user model-based interfaces. Adaptive hypermedia (AH) systems build a model of the individual user and apply it for adaptation to that user, for example, to adapt the content of a hypermedia page to the user's knowledge and goals, or to suggest the most relevant links to follow. AH systems are used now in several application areas where the hyperspace is reasonably large and where a hypermedia application is expected to be used by individuals with different goals, knowledge and backgrounds. This paper is a review of existing work on adaptive hypermedia. The paper is centered around a set of identified methods and techniques of AH. It introduces several dimensions of classification of AH systems, methods and techniques and describes the most important of them.
Article
Full-text available
Several approaches for formalising prerequisite structures on skills or competencies based on the psychological theory of knowledge space have been suggested and applied for adaptive eLearning. In this paper, we will discuss how these structures may be applied in skill management in a broader sense. After introducing some formal structures for prerequisite relationships between competencies, we will briefly present an example of an adaptive eLearning system based on this approach (APeLS). Several other aspects of the system which promise to be useful for advanced skill management are discussed. In the final part of this paper, we will discuss such broader applications of the model with respect to personal as well as to organisational skill management.
Article
Full-text available
Adaptive hypermedia is a new direction of research within the area of adaptive and user model-based interfaces. Adaptive hypermedia (AH) systems build a model of the individual user and apply it for adaptation to that user, for example, to adapt the content of a hypermedia page to the user’s knowledge and goals, or to suggest the most relevant links to follow. AH systems are used now in several application areas where the hyperspace is reasonably large and where a hypermedia application is expected to be used by individuals with different goals, knowledge and backgrounds. This paper is a review of existing work on adaptive hypermedia. The paper is centered around a set of identified methods and techniques of AH. It introduces several dimensions of classification of AH systems, methods and techniques and describes the most important of them.
Article
Full-text available
: The navigational freedom in conventional hypermedia applications leads to comprehension and orientation problems [Nielsen 1990]. Adaptive hypermedia attempts to overcome these problems by adapting the presentation of information and the overall link structure, based on a user model. This paper introduces a framework for adaptive hypermedia systems (AHS). It briefly describes some popular methods and techniques for adaptation. Examples and evaluations of existing AHS are used to illustrate the potential benefits of using adaptation in hypermedia applications. Categories and Subject Descriptors: H.1.2 Information Systems User/Machine Systems [Human information processing] H.3.5 Information Systems Online Information Services [Web-based services] H.4.3 Information Systems Communications Applications [Information browsers] H.5.1 Information Systems Multimedia Information Systems [Hypertext navigation and maps] H.5.2 Information Systems User Interfaces [Evaluation/methodology] Additional ...