Journal of Interactive Learning Research

Volume 10, Number 3/4 1999

Special Issue on Intelligent Agents for EducationalComputer-Aided Systems


Contents


Preface—IntelligentAgents for Educational Computer-Aided Systems

Lora Aroyo and Piet Kommers, Editors 235

Learning From MultipleCollaborating Intelligent Tutors: An Agent-Based Approach

Konstantinos Solomos and Nikolaos Avouris 243

A Multi-Agent Systemfor Intelligent Online Education

Colm O’Riordan and Josephine Griffith 263

Agent-Based ComputerTutorial System: An Experiment for Teaching Computer Languages(ATCL)

Mahmoud M. El-Khouly, Behrouz H. Far, and ZenyaKoono 275

Sharing an OpenLearning Space by Individualizing Agents

Jaakko Kurhila and Erkki Sutinen 287

Multi-Agent Frameworkfor Virtual Learning Spaces

Leonid Sheremetov and GustavoNúñez 301

ROADS: An Environmentfor Developing Automated Intelligent Agents to Suppport DistanceLearning

Leonard P. Wesley, Simon S.Y. Shim, Robert P. Booth, and
Shreemathi D. Atreya 321

Intelligent Agency andTutoring: The Importance of Being Timely

Enrique Espinosa and Fernando Ramos 335

Intelligent Agents toSupport Students Working in Groups Online

Janice Whatley, Geof Staniford, Martin Beer, and PhilScown 361

Interface Agent forComputer-Based Tutoring Systems

Trang Dang, Hamada Ghenniwa, and MohamedKamel 375

An Agent-OrientedApproach for Ideational Support in Learning—Integration andImpact

Lora Aroyo, Svetoslav Stoyanov, and PietKommers 389

Agent-Support forProblem Solving Through Concept- Mapping

Svetoslav Stoyanov and Piet Kommers 401


Abstracts


Special Issue Preface:Intelligent Agents for Educational Computer-Aided Systems

Editors

Lora Aroyo and Piet Kommers

University of Twente, P.O. Box 217
7500 AE, Enschede, The Netherlands

kommers@edte.utwente.nl

Before the more detailed exposition of underlying mechanisms andarchitectures for an agent-based learning support system, we wouldlike to provide you with the overall outline of the aspects that willbe addressed in this special issue:

1. Historical developments of intelligent tutoring and supportsystems

2. Agent paradigms and agent-based user support systems

3. Tendencies in agent development and application

Agent technology appears to be a promising approach to address thechallenges of modern day educational environments, influencedenormously by advanced information and Internet technologies. It hasseen a great recognition in quite a lot of educational and trainingcomputer-based activities. The existing world of education iscurrently changing rapidly in respect to all new technologies andmethods coming up on the market. This change is taking place as wellin technological as in instructional methods used in traditional andon-line education. Intelligent agents appeared to contribute ratherimportant advantages for the scientific and educational computing.They have a major influence in different application fields ofeducational systems. They provide new educational paradigms, supporttheories, and happen to be rather helpful entities for both studentsand teachers in their computer-aided learning-teaching process. Theirapplication in the educational field is mostly as personalassistants, user guides, alternative help systems, dynamicdistributed system architectures, human-system mediators, and soforth.

All these changes imply that on the one hand, increasingly complexand dynamic educational infrastructures need to be managed moreefficiently and, on the other hand, new types of educational servicesand mechanisms need to be developed and provided. It is in particularthat such services need to satisfy a diverse range of requirements,for example, personalization, adaptation, support for user mobility,support for users while coping with new types of technologies,effectiveness, information support, and so forth. Agents appear tosupport in a more efficient way those requirements in comparison toother already existing technologies. Besides the ability to processautonomy and cooperation among themselves, agents possess thecapabilities for issues such as security, both online and offlineservice providing, and so forth.

It is the aim of this special issue to introduce to a wideraudience, the state of the art in the agent technologies with respectto educational environments and computer-based systems. Of interestare also development environments, languages and tools, going alongwith agent-based systems that demonstrate the power, and theeffectiveness of agent technologies applied in the field ofeducation.

Lately an important discussion is going on with respect to thedevelopment and the design of intelligent support systems tofacilitate online and web-based study environments. The main problemis to provide easy and flexible access to various data as residing inmultiple, unstructured, heterogeneous information resources, and tointegrate those data into semantically coherent information. Virtualenvironments are rather complex environments and as such, they inviteone to apply new approaches for the support and facilitation ofongoing processes. The same is also true for virtual studyenvironments. The solution is the analogy and the metaphoric way ofthinking about virtual environments. This new approach introducesautonomous, goal-driven and sensitive objects as a main softwareentity. Following this metaphoric thinking people often refer tothose objects or pieces of software as “agents” or“intelligent agents,” where the agent metaphor enablestheir understanding, controlling, and monitoring complex environments(Travers, 1996).

When a new paradigm is introduced, the most important issues aredefinitions with major characteristics, taxonomies, operationalisingconcepts, functionality, and application. Intelligent agents havebeen characterised in a large range of definitions. An extensiveoverview of them is not the deliberate purpose of this article. Agood overview can be found in (Franklin & Graesser, 1996) and(Jennings & Wooldridge, 1995). In particular, there is no realagreement on what an agent is. Agents’ abilities varysignificantly, depending on its roles, capabilities, andenvironments. In order to describe these abilities, different notionsof agents have been introduced. Intelligent agents are introduced bymost of the researchers (Wooldridge & Jennings 1998; Jonker,1998) with four major concepts defining their behaviour: autonomy,responsiveness or reactiveness, pro-activeness and social ability.There is also a strong notion on the characteristics of agents, whichrefer to adaptiveness, pro-activity and intentionality (Denett, 1987;Meyer, 1997; Rao, 1996). There are also various taxonomies createdfor agents. According to Nwana (1996) there are seven categories ofagents—collaborative, interface, mobile, information, reactive,hybrid, and smart agents. Franklin and Graesser (1996) identify ataxonomy, which is enhanced with categories of Nwana andrestructured. Some new categories are included, such as“life-like” agents. In this context, intelligent agentshave been associated with a variety of functions, for example,personal assistants, information managers, information seekers,planning agents, co-ordination agents or collaborative schedules,user representatives, and so forth.

In this paper we take a closer look at agents from three differentpoints of view: architectural, functional, and structural.

Architectural View on Agent Technology

From an architectural point of view agents are acting as mediatorsbetween users performing specific tasks and a specific softwareapplication. They are often decomposed into functional modules, thatrefer to perception, modelling, planning, coordination, and task orplan execution. The strong point is that the agents provide theability to execute and coordinate independently and autonomouslysub-tasks, which lead to completing the major user task.

Recent trends have made it clear that software complexity willcontinue to increase dramatically in the coming decades. The dynamicand distributed nature of both data and applications require thatsoftware not merely respond to the request for information but alsoanticipate, adapt, and actively seek ways to support users. In thiscontext users expect dedicated assistance from the applications theyare using. In response to these requirements, software agents play animportant role in the human-computer interaction and in thecoordination of the internal processes of the system.

From a functional point of view we see agents in the context ofthe different roles they could be applied to. Conceptual structuresplay an important role in the functional operationalisation of theagent. They could be applied for knowledge representation and itsmanipulation mechanisms, navigation, and problem definition. In thiscontext ontology plays an important role.

The term ontology has been recently adopted by the artificialintelligence community to refer to a set of concepts or terms thatcan be used to describe some area of knowledge or build arepresentation of it (Swartout & Tate, 1999). Ontologies bringquite a fundamental change in the way systems are constructed. Alsothe combination with agents creates a real future-oriented approachin coping with the complexity of the new information age. They arereferred as vocabularies, content theories, world descriptions,shared and reusable knowledge representations, and task definitions.Agent-based intelligent systems in this respect can provide acomplete new understanding of the computer and its functionality.

Structural View on Agent Technology

The structural point of view concerns the intersection andcombination of theories, implementation, and the usage of intelligentagents in the specific application area of education. Theintroduction of agent technologies sketches the history of this newparadigm. Different points of reference are used to present a clearand structured picture of the main issues involved, concepts andconsiderations for the design and realisation of agent-basededucational software.

Contributions to this Special Issue

This volume contains selected papers on intelligent agents appliedin the field of computer-based education and learning. The idea wasto provide an overview and analysis of the ideas presented by thenumerous research projects. The articles in this journal issue aremainly oriented towards presenting multi-agent systems forcollaborative support. They represent the evolution of intelligenttutoring systems influenced by the agent approach. There are 11papers grouped around several topics:

Agent-based tutoring systems: Intelligent web-based educationalsystem, multi-agent tutoring system, collaborative intelligenttutors. This section is dedicated to tutoring systems that areenhanced by using agent technology for user-oriented education andtraining support.

Instructional design and learning theories: Modelling theintelligence in instructional processes and students learning. Theselection of articles focuses on instructional design issues andlearning theories realised by means of agent-based architectures.

Agent-based development tools and environments. This sectionprovides examples and perspective on development tools andenvironments for the realisation of agent-based educational software.It gives an overview of some existing well-known developmentapplications and presents a real time object-oriented agentdevelopment system used to build an embedded distributed rationalagent that can manage the acquisition and presentation of multi-mediainformation in a distance learning component of a course.

The following sections focus on different types of agent-basedpersonal assistants and user support tools. They present examples ofsingle user and collaborative learning support, navigation tools forlearning materials, interface agents, virtual laboratories, andsimulation environments.

This special issue covers topics and presents papers thatillustrates important points in the evolution of Intelligent TutoringSystems with the existence of the agent paradigm. Most of the paperspresent both recent prototyping work and already implemented systems,tested in real learning environments. A variety of tools have beenexplored and used for the construction of the systems, like IBM AgentBuilder Environment used by Trang Dang, Hamada Ghenniwa, and MohamedKamel for the construction of an instructional assistant interfaceagent within the Practical Algebra Tutor (PAT) system. Here we alsofind an application of Java Abstract Window Toolkit (AWT) componentsfor building interaction dialogues of the interface agent andKnowledge Interchange Format (KIF) is used to build the agent’sknowledge base.

Many of the papers included in this special issue are dealing withmulti-agent systems. The paper of Konstantin Solomonos and NikolaosAvouris presents a multi-agent system where the communicationlanguage among numerous tutoring and broker agents is based on thewell-known KQML. In this paper we also see a servlet-baseddevelopment of the agent society.

Colm O’Riordan and Josephine Griffith present interestingwork in the field of web-based educational systems focusing onagent-based support for information management and user modelling.The system adopts the agent-based approach to provide pro-activelearning by maintaining a user model, and by supporting peer learningvia multi-agent collaboration. The emphasis of this paper is on thequestion of how to take full advantage of the possibilities providedby World Wide Web by applying agents. This on the other hand, raisesquestions of how agents can help in overcoming some disadvantages ofthis medium as well.

Mahmoud M. El-Khouly, Behrouz H. Far, and Zenya Koono take theperspective of the current intelligent computer aided instructionsystems and present the advantages of applying agents in them toovercome some shortages, like language dependence and not preciseextraction methods for student’s knowledge. The authors presentintelligent agent-based tutorial systems consisting of two personalassistants for teachers and students (PAA-T and PAA-S).

Jaakko Kurhila and Erkki Sutinen present in their paper, alearning environment, in which an agent provides the user withnavigation support through multi-dimensional learning space. It takesthe perspective of comparing traditional tutoring systems with theproposed type of learning environments. The system Ahmed is anadaptive hypermedia system targeted for children with deficiencies inmental programming. An interesting new instructional concept isintroduced—learning seeds, referring to educational space itemsclosely related but higher in value to CAI frames.

The paper of Leonid Sheremetov and Gustavo Nunez presents theusage of multi-agent frameworks in virtual learning spaces. Quiteinteresting and innovative is the conceptual architecture of EVAstructured into different learning spaces and together with thepresentation of unifying framework for distributed heterogeneouscomponents in EVA. It reports research on a ConfigurableCollaborative Learning. It focuses on theoretical and practicalissues of artificial learning companions, personalised collaborativeassistants, planning, experimenting, and virtual laboratories.

A valuable contribution to the special issue is the paper ofLeonard Wesley, Simon Shim, Robet Booth, and Shreemathi Atreya. Theytake the perspective of an agent development system and give aconsistent overview of the existing technologies and developments inthis respect, for example, IBM Agent Building Environment,Standford’s Java Agent Template, the Java Expert System Shell,and many others. The authors present the ROADS system - a real timeobject-oriented agent development system used to build an embeddeddistributed rational agent that can manage the acquisition andpresentation of multi-media information in a distance-learningcomponent of a course. The ROADS system suggests how agents canprovide better and purposeful Distance Learning Environments.

Other papers deal with theoretical issues in respect toinstruction and how agents could support it. In their paper, EnriqueEspinosa and Fernando Ramos address general didactic theories andtheories of instructional system design. They present amodal-logic-driven agent system and report experimental research ofuser tests done with the prototype agent system, which makes thepaper rather relevant and an interesting contribution to the specialissue.

The article of Janice Whatley, Geof Staniford, Martin Beer, andPhil Scown reviews and synthesises the most important problemsencountered when students perform work on group projects. It presentsa multi-agent architecture for student support in their on-line groupwork. The help provided in collaborative computer aided environmentsis concentrated mainly in support of maintenance roles, such asplanning the work, task allocation, and monitoring progress, as wellas recognising problems as they arise. Agents are applied in order tosolve problemssuch as, the lack of skills, the lack of time, and theabsence of human expertise.

Finally, in the last articles of this special issue we bringtogether the latest empirical evidence on the cognitive and creativeimpact of agent-support for concept mapping, in particular forproblem solving in advanced learning settings. These article attemptsto provide the reader with a potential experimental model that shouldbe practiced for a longer time, aiming at ever more clearlypinpointing the net added value of the propagated tools and methods.We hope that this special issue also stimulates you to pursue themany still unsought metaphors and paradigms for the growing need inautonomous and still effective learning environments.

Return to Contents


Learning FromMultiple Collaborating Intelligent Tutors: An Agent-BasedApproach

Konstantinos Solomos and Nikolaos Avouris

Learning Technology Group
Electrical and Computer Engineering Department,
University of Patras
GR-265 00 Rio-Patras, Greece

N.Avouris@ee.upatras.gr

This paper describes an open distributed multi-agent tutoringsystem (MATS) and discusses issues related to learning in such openenvironments. MATS is a prototype that models a “onestudent—many teachers” learning situation. Each MATS agentrepresents a tutor, capable of teaching a distinct subject. All MATStutors are also capable of collaborating with each other for solvinglearning difficulties that their students may have. In order to buildthis prototype, the following parts of the architecture had to bedefined: an adequate agent architecture and multi-agent platform, aknowledge interchange language suitable for learning tasks, and ageneral ontology of learning environments as a foundation forknowledge sharing. MATS can be used for supporting collaboration ofheterogeneous learning objects and for this reason is an interestingparadigm of learning in the rapidly expanding, open distributed worldof knowledge surrounding us. The challenges that the learners facewhen participating in such environments are also discussed in thelast part of the paper where the learners’ roles in the MATScontext are described.

Return to Contents


A Multi-AgentSystem for Intelligent Online Education

Colm O’Riordan and Josephine Griffith

Information Technology Centre
National University of Ireland
Galway, Ireland

colmor@it.nuigalway.ie

Given the increasingly widespread use of computers, it is notsurprising that both students and course-providers are focusing moreattention on using computers as an educational aid. A popular area ofresearch has been the delivery of course material via the Internet.The majority of such courses focus predominantly upon content and donot exploit the full capabilities of the available technology. Byutilising the potential of current technology, one can provide anintelligent, personalised, and adaptive web-based education system.In our system, we adopt an agent-based approach to provide forpro-active personalised learning by maintaining a user model, and tosupport peer-peer learning via multi-agent collaboration. Our systemalso incorporates intelligent information filtering agents tofacilitate the automatic gathering of related course material. Weattempt to accurately represent users’ ability and progress andsubsequently use this representation to guide automatic modificationof content. This paper describes the system architecture—usermodelling agents, information filtering agents, and the multi-agentinteraction—and also summarises implementation details andinitial results.

Return to Contents


Agent-BasedComputer Tutorial System: An Experiment for Teaching ComputerLanguages (ATCL)

Mahmoud M. El-Khouly, Behrouz H. Far, and Zenya Koono

Saitama University, Faculty of Engineering, Informationand
Computer Sciences Department, FAR Lab
T 338, Urawa-Shi, Shimo-Okubo, 255
Saitama-ken, Japan

{elkhouly,far,koono}@cit.ics.saitama-u.ac.jp

This paper presents a new vision for intelligent computer aidedinstuction (ICAI) in the presence of agent technology. An agent-basedcomputer tutorial system consists of two sub-agents; (a) personalassistant agent for teachers (PAA-T), and (b) personal assistantagent for students (PAA-S). PAA-T that allows the teachers to copewith the knowledge base of a computer language under investigation,and add or modify the commands’ structure that will be taught.Also, this agent can generate a new tutoring dialog for a newcomputer programming language by consulting previous tutoring dialogsfor another computer programming language. PAA-S contains a studentmodel and a tutoring module. In the student model, the system canaccept free-format answers from the student, and check it against thelanguage structure. Tutoring text has been separated from thetutorial module, such that the student’s mother tongue can beused. The system is suitable for any computer procedural language(e.g., FORTRAN, PASCAL, etc.). The system has been tested in someschools, and the feedback has been taken into consideration. Usingthese kinds of agents allows us to expand their features to includecommunication with other agents and to exchange teacher’sexperiences as well as tutoring dialogs.

Return to Contents


Sharing an OpenLearning Space by Individualizing Agents

Jaakko Kurhila

Department of Computer Science
P.O.Box 26 (Teollisuuskatu 23)
FIN-00014 University of Helsinki, Finland

kurhila@cs.helsinki.fi

Erkki Sutinen

Department of Computer Sciences, Purdue University
1398 Computer Science Building
West Lafayette, IN 47907-1398, USA

We present a learning environment where an agent supports alearner through a multi-dimensional learning space by findingchallenging pieces of learning material and problem solving tasks tothe learner. The individualized path through the space helps thelearner to construct his or her own model of the topic in thelearning space. Our learning environment differs from traditionalintelligent tutoring systems. The aim is to leave the responsibilityof the pedagogics of the material to human experts creating thelearning material. The learning environment is implemented to thecontext of special education. The intended users have motorimpairments, but also difficulties in organizing a given assignment,keeping up their attention, or navigating towards a goal. Similarproblems occur frequently within other user groups but with differentlearning spaces, like those of project planning or mastery of life;the scheme presented can also be applied to these areas.

Return to Contents


Multi-AgentFramework for Virtual Learning Spaces

Leonid Sheremetov and Gustavo Núñez

Agents Laboratory, Computer Science ResearchCenter
National Technical University
(CIC-IPN), Mexico

sher@cic.ipn.mx

This article reports on the first results of the research workwithin the paradigm of Configurable Collaborative Learning, which wehave named EVA (stands for Virtual Learning Spaces in Spanish). Themain purpose of this project is to develop models, architectures, anda multi-agent environment for collaborative learning andexperimentation. Each space in EVA consists of a number of componentscomposed of a set of deliberative and auxiliary agents. The articlefocuses on theoretical and practical issues of personalizedcollaborative learning with artificial learning companions, personallearning assistants with activities planning, and experimentationactivities with agents. A unified framework for the distributedheterogeneous learning environment is defined on the basis ofdistributed component and agent models. Prototypes of agents havebeen developed using Microsoft VC++, LALO, JAVA, and JATLite for Unixand Windows platforms.

Return to Contents


ROADS: AnEnvironment for Developing Automated Intelligent Agents to SuppportDistance Learning †

Leonard P. Wesley, Simon S.Y. Shim, and Shreemathi D. Atreya

Computer, Information and Systems EngineeringDepartment
College of Engineering, San Jose State University
One Washington Square
San Jose, CA 95138

lwesley@intellexus.com, sishim@email.sjsu.edu,atreyas@earthlink.net

Robert P. Booth

Motorola, Design/Ver Tools, Core & SystemTechnology
6300 Bridgepoint Pkwy, Bldg #3
Austin, TX 78730

rbooth@ibmoto.com

We describe work that is intended to extend the state-of-the-artin intelligent agent development environments (ADEs) and is intendedto advance the use of automated agents to support distance learning(DL). A real-time object-oriented agent development system (ROADS)has been developed and used to build an embedded distributed rationalagent that manages the acquisition and presentation of multi-mediainformation in a distance learning component of an undergraduate datastructures course. Some ROADS innovations include the use of a theoryof objects as a foundation on which: (a) different agent developmentlanguages can be defined and used within a single ADE; (b)computational models of beliefs desires and intentions are readilyimplemented; (c) possible world semantics are readily supported; (d)reactivity and responsiveness are under direct dynamic control of theagent applications, and (e) a formal foundation to model cooperativemulti-agent applications is provided. Some DL innovations includenovel and effective ways to (a) model a user’s knowledge aboutcourse material; (b) manage the acquisition and presentation ofdistributed multi-media course material, and (c) profile user DLpreferences and habits. Results and examples are presented thatsuggest the design of ROADS and ROADS agents begin to bridge existingADE and DL technical gaps.

Return to Contents


Intelligent Agencyand Tutoring: The Importance of Being Timely

Enrique Espinosa

Instituto Tecnológico y de Estudios Superiores deMonterrey
ITESM-Campus Ciudad de México, Departamento deComputación
Calle del Puente 222 México D.F. 14380México

eespinos@campus.ccm.itesm.mx

Fernando Ramos

ITESM-Campus Morelos
Programa de Graduados en Informática
Paseo de la Reforma 182-A Lomas de Cuernavaca. Cuernavaca,Mor. México 62589

framos@campus.mor.itesm.mx

Instructional Design, the pedagogical technique typically used todesign computer based education software, including intelligenttutoring systems, relies on a set of correctness metrics calledInstructional Integrity. Hereby, curricula should describe, inunambiguous terms, the structure of the information any student mustacquire. A time interval is expected to have elapsed upon eachtransition among these states. It is assumed that knowledge must havebeen transferred to the student at the end of each interval. This isclearly consistent with Instructivism, since knowledge isquantifiable and incrementally administered. In reality, however,learning will occur holistically, in time. As a result, agentmeasuring and tutoring of the learning process at the end ofpredetermined causal-time intervals results in Temporal Holes whereimportant events might be taking place. We deal with these holes bymodeling the student’s learning process rather than theknowledge to be learned. We attempt this by using Agent-ProneModal-Temporal Logic Specifications on a modified Interface Model fora Datastructures Tutor not designed as an Instructional Graph. Wedemonstrate prototype software, and provide test examples withinthree well-known instructional methods: Didactic, Inquiry, andDiscovery. We conclude by presenting conclusions and further workstrands.

Return to Contents


Intelligent Agentsto Support Students Working in Groups Online

Janice Whatley

Business and Information Technology
Stockport College of Further and Higher Education
Wellington Road South, Stockport, SK1 3UQ, UK

Janice.Whatley@cs.stockport.ac.uk

Geof Staniford

Computing and Mathematical Sciences
Liverpool John Moores University
Rodney St, Liverpool, L1 1IS, UK

Martin Beer

Department of Computer Science
University of Liverpool
PO Box 147, Liverpool, L69 3BX, UK

Phil Scown

Department of Business Information Technology
Manchester Metropolitan University
Aytoun Street, Manchester, M1 3GH, UK

Agent technology is being applied where information overload is aproblem and where intelligent help for the user is required; one suchexample is online higher education. Intelligent help is traditionallysupplied by knowledge-based systems, but these usually work for asingle domain and require the user to initiate them. Agent based helpwatches the user at work and perform operations autonomously when theuser needs them. We suggest using agent technology to provide helpfor students working on group projects online. Successful group workrequires that the maintenance roles of the group are given attentionas well as the task roles. Each student working on the project willhave an agent, operating in the background, watching progress,measuring it against the plan, and taking remedial action whennecessary. These agents will interact with the other student agentsto ensure that the project is completed satisfactorily. This paperdescribes our initial investigations into the sorts of problemsencountered when students work on group projects, and describes howthe means to recognize and prevent problems will be incorporated intothe design for student group support agents. A method is describedthat explicitly involves users in the design process.

Return to Contents


Interface Agent forComputer-Based Tutoring Systems

Trang Dang

Clarica 227
King Street South
Waterloo, Ontario,N2J 4C5A Canada

Hamada Ghenniwa

Department pf Electrical and Computer Engineering
The University of Western Ontario
London, Ontario N6A 5B9 Canada

Mohamed Kamel

Systems Design Engineering Department,
University of Waterloo
Waterloo, Ontario, N2L 3G1 Canada

mkamel@uwaterloo.ca

http://pami.uwaterloo.ca/kamel.html

In this era and beyond, the constant in many business environmentsis change. There are continuous changes in business climate, laws,markets, competition, and clients’ desires. Therefore, for anorganization to survive and thrive in this era, ”life-long”training and learning for its employees becomes a necessity.Computer-based tutoring systems are playing an important role insupporting life-long learning environments. However, traditionalcomputer-based tutoring systems lack the support for many aspects ofeffective training and learning, such as personalization andcollaboration. To deal with these issues, a computer-based tutoringenvironment should be able to accommodate the constant changes of thelearners’ knowledge level and needs, as well as to the knowledgedomain. The goal is to create a collaborative learning environmentbetween the learner and the tutoring software, and to proactivelyassist him/her in achieving the learning objectives. This paperproposes an interface agent that is autonomous, goal-driven, dynamic,and collaborative. The interface agent acts as a mediator between thelearner and the tutoring system. The interface agent interacts withthe learner and the tutoring systems to provide a collaborativeenvironment. It monitors the learner’s habits and weaknesses toadapt its didactic directions. This approach also facilitates thereusability of different tutoring domains. To learners, the interfaceagent offers a flexible and customizable common interface that theycan use for different subjects. A prototype of the interface agentwas implemented using the IBM Agent Builder Environment Toolkit(ABE). It acts as a mediator between the learner and PracticalAlgebra Tutor (PAT) intelligent tutoring system for teaching algebra.In this implementation we demonstrated how an interface agent couldbe used to increase the flexibility and improve the effectiveness oftraditional computer-based learning systems.

Return to Contents


An Agent-OrientedApproach for Ideational Support in Learning—Integration andImpact

Lora Aroyo

Svetoslav Stoyanov

Piet Kommers

University of Twente
Faculty of Educational Science & Technology
P.O. Box 217, 7500 AE Enschede, The Netherlands

{aroyo, stoyanov, kommers}@edte.utwente.nl

This paper provides results from research work done in respect tothe application of agent technology within educational settings. Itfocuses on problem solving, information handling issues and ideageneration. It is based on two research system examples: Solution,Mapping, Intelligent, Learning, Environment (SMILE) Creator and Agentbased Information Management System (AIMS). Both systems presentapproaches for solutions to some of the basic problems within thecontext of computer based education and training, for example,adaptive learner support, problem solving, navigation, informationstructuring, presentation, and retrieval. They apply theconcept-mapping approach as a basic mechanism for agents’behaviour, information presentation technique, and instructionalsupport. The agent-oriented approach is also applied in AIMS for theoverall system architecture and design, where agents are the basicsystem modules. This paper reflects on the general approach foragents’ educational application presented in the papers of thisspecial issue. It builds up a theoretical prototype of the generalmovement in the field and summarises its added value for learningtechnology.

Return to Contents


Agent-Support forProblem Solving Through Concept- Mapping

Svetoslav Stoyanov and Piet Kommers

University of Twente
Faculty of Educational Science and Technology
Division of Educational Instrumentation
P.O. Box 217, 7500 AE Enschede, The Netherlands

{stoyanov, kommers} @edte.utwente.nl

This article presents an experimental verification of ahypothetical construct explaining the basic mechanism behind thebehavior of an intelligent agent implemented in the Solution,Mapping, Intelligent, Learning Environment (SMILE) performancesupported system. The SMILE agent, (called “facilitator”)supports a user in learning and applying a new concept mapping methodfor solving ill-structured problems. This article emphasizes thefacilitator’s master performer model of behavior. The modelreflects upon the SMILE Maker as a problem-solving tool andespecially upon the SMILE concept mapping method.

The SMILE concept mapping method is based upon the fourcharacteristics of: expressiveness, extension, externalization, andentireness (4E) hypothetical construct. The facilitator as a masterperformer of the SMILE concept mapping method reacts to theuser’s behavior accordingly to the extent that thesecharacteristics are accomplished.

Return to Contents