Technology enhanced learning takes place in many different forms and contexts, including formal and informal settings, individual and collaborative learning, learning in the classroom, at home, at work, and outdoor in real life situations, as well as desktop-based learning and learning by using mobile devices. Environments range from desktop-based learning systems such as learning management systems, which present learners with learning material and activities, to mobile, pervasive, and ubiquitous learning environments which are used in real life settings and enable learners to learn from real learning objects. In each of these forms and contexts, adaptive and intelligent support has potential to contribute in making such learning environments more personalized, user-friendly, and effective in supporting learners in learning.
Intelligent and Adaptive Learning Systems: Technology Enhanced Support for Learners and Teachers focuses on how intelligent support and adaptive features can be integrated in currently used learning systems and discusses how intelligent and adaptive learning systems can be improved in order to provide a better learning environment for learners. This book provides academics as well as professional practitioners innovative research work for enhancing learning environments with adaptively and intelligent support in different contexts and settings, ranging from provision of courses and assessment in formal desktop-based learning systems to learning environments that support collaborative, informal, ubiquitous learning.
The many academic areas covered in this publication include, but are not limited to:
- Automatic Composition of Exams and Creation Of Questions
- Curriculum Planning
- Group Formation
- Individual Support of Learners in Groups
- Intelligent and Adaptive Feedback for Learners
- Peer Assessment
- Presentation and Navigation Support
- Sequencing of Learning Objects
Table of Contents and List of Contributors
PrefaceSabine Graf, Fuhua Lin, Kinshuk, and Rory McGreal
Athabasca University, Canada
Intelligent and adaptive learning systems aim at providing learners with an environment that adapts intelligently to their needs, presenting learners with suitable information, learning material, feedback and recommendations based on their individual characteristics and situation, and therefore helping to support learners making learning easier for them. The term “adaptive” refers to the functionality of the system to automatically provide different learning experiences to learners with different characteristics and needs. An adaptive system considers, for example, the learners’ prior knowledge, preferences, learning goals, misconceptions, learning styles, and cognitive abilities. The term “intelligent” means that a system uses artificial intelligence techniques in order to support learners or identify their characteristics, needs, and/or situation.
The first intelligent and adaptive learning systems were developed in the 1990s, having their roots in Adaptive Hypermedia and Intelligent Tutoring Systems. They included systems such as Interbook (Brusilovsky, Schwarz & Weber, 1996a), ELM-ART (Brusilovsky, Schwarz & Weber, 1996b), CALAT (Nakabayashi et al., 1995) and De Bra’s adaptive hypermedia course (De Bra, 1996). Recently, many research investigations have been conducted in the area of intelligent and adaptive learning, resulting in the development of numerous systems. The first intelligent and adaptive learning systems focused on considering and identifying the knowledge state and progress of students in a course or task. Since then, a broader set of characteristics, needs, and states of learners has been investigated and considered in current systems. These include, for example, students’ learning styles, cognitive abilities, affective states, learning goals, interests, misconceptions, and so on. These newer systems aim at identifying these characteristics, needs, and states dynamically by observing the students’ behaviour, progress, and interaction with the system and applying artificial intelligence techniques in order to build and update the student model.
Nowadays, technology enhanced learning takes place in many different forms and contexts, including formal and informal settings, individual and collaborative learning, learning in the classroom, at home, at work, and outdoors in real life situations using different devices such as desktop computers and mobile devices. Learning environments range from desktop-based learning systems such as learning management systems, which present learners with learning material and activities, to mobile, pervasive, and ubiquitous learning environments, which are used in real life settings and enable learners to learn from physical learning objects. In each of these forms and contexts, adaptive and intelligent support has great potential to make such learning environments more personalized, user-friendly, and effective in supporting learners in learning.
Besides focusing on supporting learners, recent intelligent and adaptive learning systems also aim at providing intelligent support and adaptive experiences for teachers and course developers. In recent years, the need of providing sufficient support for teachers and course developers in creating and managing online courses in intelligent and adaptive learning systems has been widely identified. Therefore, recent research and development has been focusing on how to support teachers and course developers in using intelligent and adaptive learning systems, including creating, designing, and managing adaptive courses and intelligent features. Furthermore, intelligent and adaptive learning systems are aimed at facilitating regular teaching processes, enabling teachers to better monitor students’ progress and provide more informed feedback and support to their students.
This book presents innovative research on intelligent and adaptive learning systems and shows how adaptivity and intelligent support can enrich emerging areas of technology enhanced learning. This support for learners and/or teachers is facilitated through intelligent techniques, while incorporating the learners’ and/or teachers’ individual needs and characteristics. This collection is divided into six sections: the generation and provision of intelligent and adaptive courses; intelligent and adaptive feedback, testing, and assessment; the potential and use of semantic technologies in intelligent and adaptive learning systems; the enhancement of collaborative learning through adaptivity and intelligent support; the application of adaptivity and intelligent support for learning in virtual worlds; and mobile, pervasive, and ubiquitous learning enhanced through adaptivity and intelligent support.
The book deals with models, architectures, developments, and evaluations of intelligent and adaptive learning environments and systems, as well as with best practices of using adaptive and intelligent learning environments and systems. In addition, issues such as student modeling, authoring, and usability aspects in the abovementioned areas are discussed.
The first section introduces current research on intelligent and adaptive course generation and course provision in learning systems considering learners’ characteristics, behaviour, and needs, and/or providing intelligent support for learners and/or teachers. In the first chapter, Sampson and Karampiperis discuss one of the core issues in intelligent and adaptive learning systems, namely design approaches for the definition of adaptation behaviour in learning systems. Furthermore, the authors look into how to evaluate the performance of the design of adaptation models, which describe the rules and behaviour of adaptive learning systems. In the second chapter, Khribi, Jemni, and Nasraoui provide an overview of another important issue in intelligent and adaptive learning systems, discussing personalization issues in technology enhanced learning based on recommendation systems and Web mining technologies. Next, Peña de Carrillo, et al. introduce a context modeling approach that supports teachers and tutors, helping to reinforce their skills and abilities in carrying out reengineering processes on their pedagogical scenarios. This enables teachers and tutors to adapt their teaching actions, considering their learners’ profiles and performances in technology enhanced learning environments. In the next chapter, Tan, Ullrich, and Shen discuss how cultural issues can be considered in the course generation process of adaptive learning systems and demonstrate the changes that are required to adjust an adaptive learning system for use in another culture. The last chapter in this section, written by Butakov, et al., presents a theoretical framework that extends the capabilities of learning management systems with a multi-agent based platform using intelligent agents for performing various tasks to improve course provision.
The second section deals with intelligent and/or adaptive techniques for providing feedback to learners as well as testing and assessing learners’ performance in a course. The first two chapters focus on providing intelligent feedback. Ifenthaler discusses the theoretical background for an intelligent feedback approach and introduces two intelligent and automated model-based feedback tools. These tools provide feedback based on natural language text input as well as use graphical representations based on the learners’ prior knowledge in order to promote the learners’ self-regulated learning. In the next chapter, Kong introduces an Internet-based intelligent learning environment for fraction learning, focusing on the Next Step Support feature that provides learners with intelligent feedback to break the impasse in fraction operations. The third chapter in this section, written by Zhou, discusses the role of self-assessment tests in intelligent tutoring systems and provides an in-depth analysis and synthesis of current research and developments in this area. Furthermore, a model for direct self-assessment is presented, emphasizing learners’ initiatives as well as an external scaffold for intelligent self-assessment. The last two chapters in this section deal with assessing learners’ competencies and performance. Bodea and Dascalu introduce a tool for adaptive e-assessment for project management competences, using the computer adaptive testing (CAT) principle. The effectiveness of the tool is demonstrated through an evaluation with 150 students. Subsequently, Bescherer et al. discuss intelligent assessment in mathematics education using semi-automatic feedback. In their chapter, the authors present a model for intelligent assessment and introduce several prototype applications of semi-automatic feedback and assessment based on this model.
The third section discusses the use of semantic technologies and ontologies for enhancing intelligent and adaptive learning systems. The first chapter in this section, written by Liu et al., discusses the automatic construction and use of directed semantic relations between learning objects in order to scaffold learners’ semantic reasoning and enable the provision of adaptive learning content based on semantic relations. An approach for directed semantic relation graph construction is introduced and a learning scenario for demonstrating the use of such a graph is presented. The next two chapters use semantic technologies and ontologies for modeling learners’ context, culture, and competencies. The chapter written by Gasparini et al. focuses on modeling context and cultural information through ontologies. They introduce a personalized approach called ADAPTSUR that aims at improving the personalization capabilities of learning systems by considering contextual and cultural aspects. Furthermore, the integration of this approach into two intelligent and adaptive learning systems is demonstrated. The chapter written by Kumar focuses on tracing metacognitive competencies related to self-regulation from learning activities of online learners through an ontology-based mechanism. This mechanism aims at providing opportunities for authentic real-time feedback that not only consider learners’ task-specific competencies but also their metacognitive competencies. The next chapter, written by Paquette and Marino, contributes to the adaptive Semantic Web and introduces a personalized assistance model that is based on ontology modeling and Semantic Web techniques, helping learners processing task-based scenarios and finding resources suited to their knowledge, competency, and context of use. The last chapter in this section, written by Charlton and Magoulas, deals with adaptation and personalization in the creation of learning designs, and introduces a context-aware adaptation framework that uses Semantic Web technologies and ontological models for supporting the creation of learning designs, providing teachers and course designers with adaptive and personalized experiences.
The fourth section deals with intelligent techniques and/or adaptation features that facilitate and improve collaborative learning. In the first chapter of this section, Wei et al. discuss the recording of live instructional activities conducted in synchronous cyber classrooms, including lectures, demonstrations and discussions. The authors explore the functional requirements for the types of instruction modes and conducted an analysis to find the best match between the instruction modes and the essential functions of recording tools, aiming at providing learners with the most effective tools to learn in a cyber classroom setting. The second chapter, written by Whatley, focuses on using agent technologies for providing intelligent support to students, supporting them in getting started on their team projects by facilitating the allocation of tasks to individuals and agreeing on ground rules for the team. A software agent system is introduced, and the evaluation of the system by students is discussed.
The fifth section discusses how virtual worlds, supported by embedded intelligence as well as adaptive and intelligent features, can be used for learning. The first chapter in this section, written by Heller and Procter, focuses on embodied and embedded intelligence in virtual worlds and introduces the agent actors Freudbot, a computer-controlled intelligent avatar who responds intelligently to his surroundings in Second Life and interacts and communicates with other avatars controlled by learners, engaging them in learning through natural language conversations. The next chapter, written by Chiang et al., introduces how virtual worlds can be used for improving language learning, benefitting from the embedded intelligence and social character of these worlds. Furthermore, this chapter demonstrates two successful case studies of language learning in Second Life.
The last section discusses how adaptivity and intelligent support can be provided in mobile, pervasive, and ubiquitous learning, with the goal of enhancing learners’ experiences, while learning from their mobile devices. The first chapter in this section, written by Molnar and Muntean, discusses the consideration of costs of the educational multimedia content delivery in mobile learning and introduces an e-learning framework that predicts a learner’s economic behaviour and takes it into account when delivering educational multimedia content. Furthermore, a mechanism for reducing the cost of the educational content delivery over multimedia networks is presented. In the next chapter, Kumar, Chang, and Leacock focus on enhancing learners’ academic writing competence through the use of personalized mobile learning and mixed-initiatives. Two studies are presented, demonstrating ways of recording traces of problem solving and writing processes that can be used for providing personalized support for improving learners’ academic writing competencies.
Brusilovsky, P., Schwarz, E., & Weber, G. (1996a). A tool for developing hypermedia-based ITS on WWW. In C. Frasson, G. Gauthier, & A. M. Lesgold (Eds.), Workshop on Architectures and Methods for Designing Cost-Effective and Reusable ITSs at the International Conference on Intelligent Tutoring Systems, Montreal, Canada.
Brusilovsky, P., Schwarz, E., & Weber, G. (1996b). Elm-Art: An intelligent tutoring system on World Wide Web. In C. Frasson, G. Gauthier, & A. M. Lesgold (Eds.), International Conference on Intelligent Tutoring Systems, Lecture Notes in Computer Science 1086 (pp. 261-269). Montreal, Canada: Springer.
De Bra, P. (1996). Teaching hypertext and hypermedia through the Web. Journal of Universal Computer Science, 2(12), 797-804.
Nakabayashi, K., Koike, Y., Maruyama, M., Touhei, H., Ishiuchi, S., & Fukuhara, Y. (1995). An intelligent tutoring system on World Wide Web: Towards an integrated learning environment on a distributed hypermedia. In H. Maurer (Ed.), World Conference on Educational Multimedia, Hypermedia, and Telecommunications (pp. 488-493). Graz, Austria: AACE Press.
Author(s)/Editor(s) BiographySabine Graf has a PhD from Vienna University of Technology, Austria, and is presently an Assistant Professor at Athabasca University, School of Computing and Information Systems, in Canada. Her research expertise and interests include adaptivity and personalization, student modeling, ubiquitous and mobile learning, artificial intelligence, and collaborative learning technologies. She has published more than 60 peer-reviewed journal papers, book chapters, and conference papers in these areas, of which three conference papers were awarded with the best paper award. Dr. Graf is Executive Board Member of the IEEE Technical Committee on Learning Technologies, Editor of the Learning Technology Newsletter, a publication of the IEEE Computer Society’s Technical Committee on Learning Technology (TCLT), and Associate Editor of the International Journal of Interaction Design and Architectures. She is an active member of the research community, serving as editorial board member of three international journals, workshop chair and organizer of eight international workshops, doctoral consortium chair at three international conferences, and guest editor of three special issues. Furthermore, Dr. Graf has been invited to given keynote/invited talks at universities/companies/conferences in Austria, Canada, Colombia, New Zealand, Taiwan, and UK.Fuhua Lin is a Professor and the Centre Chair of the School of Computing and Information Systems, Faculty of Science and Technology, of Athabasca University, Canada. Dr. Lin has been conducting research in Computers in Education since 1986. He obtained his PhD in Virtual Reality from Hong Kong University of Science and Technology in 1998. Prior to working in Athabasca University, Dr. Lin was an assistant research officer at the Institute for Information Technology (IIT) of the National Research Council (NRC) of Canada. Dr. Lin conducted post-doctoral research at the University of Calgary during 1998-1999.
Dr. Lin has garnered international recognition for his research in Artificial Intelligence (AI) in education and agent-based educational systems. His current research interest is applying AI technology through constructing effective and efficient algorithms to address challenges that may exist in traditional educational systems and to enhance online and distance learning environments, e.g. incorporating intelligence into virtual worlds for e-learning to build engaging, personalized, and interactive social virtual learning environments for online learning. He is leading a research group, the Intelligent Educational Systems group, consisting of PhD students, MSc students, researchers, and international visiting scholars. As principal investigator, Dr. Lin has received various external research grants and awards.
Dr. Lin has more than 80 publications, including edited books, journal papers, book chapters, conference papers, and reviews. He is the editor of the book Designing Distributed Learning Environments with Intelligent Software Agents published by IGI Global and is co-editor of the book Intelligent and Adaptive Learning Systems: Technology Enhanced Support for Learners and Teachers. Dr. Lin is the Editor-in-Chief of the International Journal of Distance Education Technologies. He has served as an invited reviewer for many international journals. For more information about Dr. Lin's research, please visit: oscar.athabascau.ca.Kinshuk is NSERC/iCORE/Xerox/Markin Industrial Research Chair for Adaptivity and Personalization in Informatics, Associate Dean of Faculty of Science and Technology, and Full Professor in the School of Computing and Information Systems at Athabasca University, Canada. His work has been dedicated to advancing research on the innovative paradigms, architectures, and implementations of learning systems for individualized and adaptive learning in increasingly global environments. His main research interests lie in the areas of adaptive learning systems, cognitive profiling, and mobile learning technologies. He is the Founding Chair of IEEE Technical Committee on Learning Technology and the Editor of the SSCI indexed Journal of Educational Technology & Society. He has been involved in numerous large-scale research projects for exploration based adaptive educational environments and has published over 300 research papers in international refereed journals, conferences, and book chapters. Kinshuk has also organized and chaired numerous international conferences and workshops in the area of advanced learning technologies.Rory McGreal is a Professor of Computer Technologies in Education and the Associate Vice President of Athabasca University – Canada’s Open University based in Alberta, Canada. He is also a UNESCO Chair in Open Educational Resources. He was previously the Executive Director of TeleEducation NB, a bilingual New Brunswick e-learning network. He previously was a supervisor at Contact North, a bilingual distance education network in Northern Ontario. He has also worked abroad in the Middle East, Seychelles (Indian Ocean), and Europe. He has been honored with the Wedemeyer Award for Distance Education practitioner. He researches the implementation and management of distance education systems and networks from technological, pedagogical, and policy perspectives. His present research interests include the use of open educational resources and standards in technology assisted learning, particularly in the development and application of learning objects. He is also researching how these would be applied and formatted on mobile devices for m-learning.
Martha Burkle, SAIT Polytechnic, Canada
Paloma Díaz, Universidad Carlos III de Madrid, Spain
Andreas Holzinger, Medical University Graz (MUG), Austria
Chen-Chung Liu, National Central University, Taiwan
Srinivasan Ramani, IIIT-Bangalore, India
Jarkko Suhonen, University of Eastern Finland, Finland
Chunsheng Yang, National Research Council, Canada