Adaptive Educational Systems Research Articles

Using an affective multimedia learning framework for distance learning to motivate the learner effectively

The aim of this paper is to present the affective multimedia learning framework of the MENTOR as well as the web and multimedia technologies which were used for its implementation. The MENTOR is an affective web-based adaptive educational system for distance learning. The basic concern of MENTOR is to retain the student|s emotional state positive during the learning process. To achieve this, MENTOR incorporates an affective module which enhances the traditional learning practices with an affective multimedia dimension. The foremost and endmost goal of MENTOR is to provide the learner with a more personalised and friendly multimedia environment for learning, according to his personality, mood and emotions.

Adaptive distance learning and testing system

AbstractUser models are essential to e‐learning systems, giving students learning continuity, tutors evidence of students' progress, and both a way to personalize students' learning materials to their abilities and preferences. Personalizing information has long been the motivation behind developing e‐learning systems. Adaptive educational systems attempt to maintain a learning style profile for each student and use this profile to adapt the presentation and navigation of instructional content to each student. This kind of system adapts the learning process on the basis of the student's learning preferences, knowledge, and availability. One such Web‐based tool is built at the Business School of Professional Studies in Blace (the system of intelligent evaluation using tests), which infers student knowledge using adaptive testing. The knowledge is not evaluated according to fixed standards, but it depends on individual characteristics of each student, therefore, the learning style which is the most suitable. This system is part of the integrated assessment system inside of integrated curriculum. © 2010 Wiley Periodicals, Inc. Comput Appl Eng Educ 21:E2–E13, 2013

Evaluating and improving adaptive educational systems with learning curves

Personalised environments such as adaptive educational systems can be evaluated and compared using performance curves. Such summative studies are useful for determining whether or not new modifications enhance or degrade performance. Performance curves also have the potential to be utilised in formative studies that can shape adaptive model design at a much finer level of granularity. We describe the use of learning curves for evaluating personalised educational systems and outline some of the potential pitfalls and how they may be overcome. We then describe three studies in which we demonstrate how learning curves can be used to drive changes in the user model. First, we show how using learning curves for subsets of the domain model can yield insight into the appropriateness of the model’s structure. In the second study we use this method to experiment with model granularity. Finally, we use learning curves to analyse a large volume of user data to explore the feasibility of using them as a reliable method for fine-tuning a system’s model. The results of these experiments demonstrate the successful use of performance curves in formative studies of adaptive educational systems.

Adaptation provisioning with respect to learning styles in a Web‐based educational system: an experimental study

AbstractPersonalized instruction is seen as a desideratum of today's e‐learning systems. The focus of this paper is on those platforms that use learning styles as personalization criterion called learning style‐based adaptive educational systems. The paper presents an innovative approach based on an integrative set of learning preferences that alleviates some of the limitations of similar systems. The adaptive methods used as well as their implementation in a dedicated system (WELSA) are presented, together with a thorough evaluation of the approach. The results of the experimental study involving 64 undergraduate students show that accommodating learning styles in WELSA has a beneficial effect on the learning process.

A Unified Learning Style Model for Technology-Enhanced Learning

This paper deals with the use of learning styles in technology-enhanced learning by introducing a “Unified Learning Style Model” (ULSM). The article aims at providing answers to three main questions: “What is ULSM?”, “Why do we need it?” and “How can we use it?” First, a critical analysis regarding learning styles is provided; the identified challenges are addressed by proposing the use of a new model, specifically designed for TEL use. This model integrates learning preferences extracted from several traditional learning style models, related to perception modality in a way for processing and organizing information, as well as motivational and social aspects. A detailed description of the ULSM components is provided together with its rationale and its advantages. The practical applicability of the model is also shown by briefly introducing an adaptive web-based educational system based on it (called WELSA).

PRELIMINARY EVALUATION OF A NEGOTIABLE STUDENT MODEL IN A CONSTRAINT-BASED ITS

Previous research on adaptive educational systems has shown that allowing the student to view their student model is useful in the learning process. Open student models help support meta-cognitive processes, such as self-assessment and reflection, and at the same time increase the student's trust in the system. Negotiable student models take this a step further, and allow students to negotiate and potentially modify their model. Very few negotiable student models have been implemented, and only in relatively simple systems, not integrated into a complex Intelligent Tutoring System (ITS). Therefore, it is not clearly known whether negotiable student models pose a significant advantage over simpler open student models. This research implements a basic negotiable student model into a version of a complex and internationally deployed ITS. Subjective evaluation is performed, and shows promising results. Participants felt the negotiable student model was both useful for learning, and enjoyable to use. With a few improvements, this negotiable student model implementation could be used in a wide-scale objective analysis to help determine the usefulness of negotiable student models.

Exercises recommending for limited time learning

Abstract In this paper we propose a method for personalized recommendation of assignments (tasks or exercises) in an adaptive educational system. Our main goal is to help students to achieve better performance in tests. To achieve this we enhance existing adaptive navigation approaches by considering the limited time for learning. Our strategy is to cover all the required topics at least to some extent rather than learn few topics perfectly. The proposed method uses utility-based recommending and conceptbased knowledge modeling. We evaluate our approach in the domain of learning programming.

A Survey on Recent Patents Regarding Intelligent Educational Systems

Computer-based educational systems are becoming increasingly important in all levels and types of education. Intelligent Educational Systems (IESs) are computer-based educational systems encompassing Artificial Intelligence schemes to increase the effectiveness of the learning process. In this paper, we survey patents regarding IESs. As IESs we consider either Intelligent Tutoring Systems (ITSs) or Adaptive Educational Hypermedia Systems (AEHSs) incorporating intelligent techniques. We first present indicative functions implemented in the three basic components of an IES: the domain knowledge, the user (or student) modeling unit and the pedagogical module. Afterwards, we focus on representative patents concerning IESs and present the corresponding work. At the end, we outline current and future developments regarding IESs. Keywords: Intelligent tutoring systems, adaptive educational hypermedia systems, intelligent educational systems, artificial intelligence in education, intelligent E-learning systems, intelligent computer-based training systems, artificial intelligence in Elearning

Learning styles and cognitive traits – Their relationship and its benefits in web-based educational systems

Different learners have different needs; they differ, for example, in their learning goals, their prior knowledge, their learning styles, and their cognitive abilities. Adaptive web-based educational systems aim to cater individual learners by customizing courses to suit their needs. In this paper, we investigate the benefits of incorporating learning styles and cognitive traits in web-based educational systems. Adaptivity aspects based on cognitive traits and learning styles enrich each other, enabling systems to provide learners with courses which fit their needs more accurately. Furthermore, consideration of learning styles and cognitive traits can contribute to more accurate student modelling. In this paper, the relationship between learning styles, in particular the Felder–Silverman learning style model (FSLSM), and working memory capacity, a cognitive trait, is investigated. For adaptive educational systems that consider either only learning styles or only cognitive traits, the additional information can be used to provide more holistic adaptivity. For systems that already incorporate both learning styles and cognitive traits, the relationship can be used to improve the detection process of both by including the additional information of learning style into the detection process of cognitive traits and vice versa. This leads to a more reliable student model.

Supporting design decisions for modeling adaptation in tutoring WEB systems

Adaptation or personalization is the key word for Educational WEB based systems. Nevertheless, the absence of a personalization model that could make possible to reason about, to support, to analyze the design of a Personalized Tutoring WEB System (PTWS), a kind of Adaptive Educational Hypermedia System (AEHS), is a great inconvenience. The weakness of the existing approaches is the lack of a justifiably process or method to identify and structuralize adaptation constituents and determinants, as well as to define adaptation rules. In current research, these aspects are unclearly treated. Aiming at overcoming such weakness, this paper presents an approach of how to support design decisions for modeling Personalized Tutorial Web System. Keywords: adaptation, adaptation modeling, adaptive tutorial WEB system.

An Experimental Assessment of the Use of Cognitive and Affective Factors in Adaptive Educational Hypermedia

In order to assess the positive effect and validity of personalization on the basis of users' cognitive and emotional characteristics, this study presents three subsequent experiments. The first experiment explores the relationship of cognitive style and users' eye gaze behavior as to validate this specific psychological construct in the context of educational hypermedia. The second and third experiments present the effect of a set of human factors (cognitive style, visual working memory span, control/speed of processing, and anxiety) in an adaptive educational system. The eye tracking experiment demonstrated that eye gaze patterns are robustly related to cognitive style (n = 21), while matching the instructional style to users' characteristics was revealed to be statistically significant in optimizing users' performance ( n = 219), with the exception of control/speed of processing. Based on this empirical assessment, this paper argues that individual differences at this intrinsic level are important and adaptation on these parameters through personalization technologies may have a positive effect on learning performance.

On the use of adaptive instructional images based on the sequential–global dimension of the Felder–Silverman learning style theory

An adaptive educational system that uses adaptive presentation is presented. In this system fragments of different images present the same content and the system can choose the one most relevant to the user based on the sequential–global dimension of Felder–Silverman's learning style theory. In order to retrieve the learning style of each student the Felder–Soloman ILS questionnaire is used. A prototype adaptive educational system was developed and pilot tested. Evaluation of the prototype system was based on the USE questionnaire. Statistical analysis was performed using the results of the ILS questionnaire, as well as using the results of USE questionnaires completed by students in order to evaluate the pilot application of the prototype adaptive educational system. The results of the statistical analysis are presented and conclusions for future development of adaptive educational systems are discussed.

Applying Web usage mining for personalizing hyperlinks in Web-based adaptive educational systems

Nowadays, the application of Web mining techniques in e-learning and Web-based adaptive educational systems is increasing exponentially. In this paper, we propose an advanced architecture for a personalization system to facilitate Web mining. A specific Web mining tool is developed and a recommender engine is integrated into the AHA! system in order to help the instructor to carry out the whole Web mining process. Our objective is to be able to recommend to a student the most appropriate links/Web pages within the AHA! system to visit next. Several experiments are carried out with real data provided by Eindhoven University of Technology students in order to test both the architecture proposed and the algorithms used. Finally, we have also described the meaning of several recommendations, starting from the rules discovered by the Web mining algorithms.

Interactive Problem Solving Support in the Adaptive Educational Hypermedia System MATHEMA

This paper describes the interactive problem solving support offered by our adaptive educational hypermedia system called MATHEMA. The general goal of the MATHEMA is the support of senior high school students or the beginners of higher education, through an interactive and constructivist environment, in learning physics (electromagnetism) individually and/or collaboratively, and to overcome their possible misconceptions and learning difficulties. Initially, a review of related work about the implemented AEHS/ITS and the didactic design principles of the MATHEMA are presented. Through the interactive problem solving, the system supports the students in solving electromagnetism problems, individually and/or collaboratively, by following an activity that is based on the experimentation with simulations, explorations, guided discovery, and collaboration didactic approaches. An experimental study with senior high school students showed that they improve their performances when following this activity. A questionnaire that we gave to the students to express their opinion about our system helped us to improve the quality of the courses.

An architecture for making recommendations to courseware authors using association rule mining and collaborative filtering

Nowadays we find more and more applications for data mining techniques in e-learning and web-based adaptive educational systems. The useful information discovered can be used directly by the teacher or author of the course in order to improve instructional/learning performance. This can, however, imply a lot of work for the teacher who can greatly benefit from the help of educational recommender systems for doing this task. In this paper we propose a system oriented to find, share and suggest the most appropriate modifications to improve the effectiveness of the course. We describe an iterative methodology to develop and carry out the maintenance of web-based courses to which we have added a specific data mining step. We apply association rule mining to discover interesting information through students' usage data in the form of IF-THEN recommendation rules. We have also used a collaborative recommender system to share and score the recommendation rules obtained by teachers with similar profiles along with other experts in education. Finally, we have carried out experiments with several real groups of students using a web-based adaptive course. The results obtained demonstrate that the proposed architecture constitutes a good starting point to future investigations in order to generalize the results over many course contents.

Distributed Intelligent Systems

The first edition of the International Symposium on Intelligent and Distributed Computing —IDC'2007, took place on October 18–20, 2007 in Craiova, Romania. According to these who participated, Fall was beautiful in Craiova—as can be seen on the photograph below. While the Symposium itself covered a large spectrum of issues involved in Intelligent Computing, for this Special Issue we have selected these that match the specific focus of the SCPE. Therefore, out of 33 papers published in Symposium Proceedings we have selected the following six. In Studying SVM Method's Scalability Using Text Documents, D. Morariu, M. VinA£an, and L. VinA£an consider application of the SVN method to the case of automatic classification of large sets of text documents. They pay particular attention to the scalability of the approach and propose a method that allows working with very large data sets without increasing exponentially the training time and without significantly decreasing the classification accuracy. Next, in Learning Objects' Architecture and Indexing in WELSA Adaptive Educational System, E. Popescu, C. BAƒdicAƒ, and P. Trigano propose ways of organizing learning material in an adaptive educational hypermedia system. They are particularly interested in use of instructional metadata to facilitate detection of student learning style and application of adaptation techniques. Implementation of the proposed approach in the WELSA system is presented and discussed. Paper A Link-cluster Route Discovery Protocol for Ad Hoc Networks, by D. Bein, A. K. Datta and S. Yellenki introduces a route discovery algorithm for MANETs. This algorithm attempts at minimizing number of clusterheads and gateway nodes to avoid storing redundant data. Furthermore, it adapts to arbitrary movement of nodes, and joining and/or leaving of existent nodes. Focus of the next contribution entitled The Dilemma of Trust: a Social Network Based Approach, by V. Carchiolo, A. Longheu, M. Malgeri, G. Mangioni, and V. Nicosia studies how social networks can be usefully exploited in addressing the question of trust. In their approach, authors try to reproduce real-life behavior of humans when they establish and maintain trust relationships and utilize this approach to build an effective and efficient model for trust management. Next, in APP: Agent Planning Package, S. TosiA‡, M. RadovanoviA‡ and M. IvanoviA‡ introduce APP, a domain independent Agent Planning Package, which facilitates creation of intelligent agents. Within the APP, agents can generate plans for their operating environment, as well as execute them and supervise the execution. Finally, in Knowledge Processing for Web Search—an Integrated Model and Experiments, P. Gurský, T. Hor­vath, J. Jirasek, R. Novotný, J. Pribolova, V. Vanekova and P. Vojtas propose a model of a middleware system enabling personalized web search for users with different preferences. Their approach integrates inductive and deductive tasks as well as fuzzy sets and logic to find user preferences and consequently best objects. The proposed model was implemented and results of experiments are discussed. Hoping that the above summarized collection of papers will be of interest to SCPE readers we would also like to invite everyone to the second edition of the IDC Symposium, which will take place on September 18-20, 2008, in Catania, Italy ( http://idc08.diit.unict.it/ ). Maria Ganzha and Marcin Paprzycki, IBS PAN, Warszawa

Learning Objects' Architecture and Indexing in WELSA Adaptive Educational System

In this paper we present an intelligent way of organizing learning material in an adaptive educational hypermedia system. We describe the use of instructional metadata which facilitates both the detection of student learning style and the application of various adaptation techniques. The advantage of our approach is that it is independent of a particular learning style model. Furthermore, the author has to supply only the annotated learning content (the static description) while the adaptation logic (the dynamic description) is provided by the system. The approach is implemented in an adaptive educational system called WELSA and illustrated with a course module in the area of Artificial Intelligence.

Adapting to intelligence profile in an adaptive educational system

Learning characteristics, as informed by research, vary for each individual learner. Research suggests that knowledge is processed and represented in different ways and that students prefer to use different types of resources in distinct ways. However, building Adaptive Educational systems that adapt to different learning characteristics is not easy. Major research questions exist such as: how are the relevant learning characteristics identified, how does modelling of the learner take place and in what way should the learning environment change for users with different learning characteristics? EDUCE is one system that addresses these challenges by using Gardner's theory of multiple intelligences (MI) as the basis for dynamically modelling learning characteristics and for designing instructional material. This paper describes a research study, using EDUCE, that explores the effect of using different adaptive presentation strategies and the impact on learning performance when material is matched and mismatched with learning preferences. The results suggest that students with low levels of learning activity, and who use only a limited number of the resources available, have the most to benefit from adaptive presentation strategies and that surprisingly learning gain increases when they are provided with resources not normally preferred.

An adaptive web-based system for learning programming

This paper presents an approach to learning programming by novice programmers through a web-based adaptive educational system called ALEA (Adaptive LEArning). ALEA supports learning programming by generating sequences of program examples that serve as exercises for a learner. The sequence is adapted to the needs of individual learners. At present, ALEA contains more than a hundred Lisp and Prolog program examples. The program examples are presented as specific instances of program schemata, which facilitate understanding of basic programming principles. We also discuss our experience in using web-based support for teaching programming.

Identification of learning styles online by observing learners’ browsing behaviour through a neural network

AbstractIdentification of individual learning style is important when developing adaptive educational hypermedia systems. Current systems ask learners to complete questionnaires to identify their learning styles, which might not be appropriate in some contexts. The goal of this research is to identify the learner's learning style by simply observing his/her browsing behaviour without asking the learner to answer any questions or filling out any form. It is implemented through a multi‐layer feed forward neural network (MLFF). Browsing behaviour, in this research, includes three factors, the use of embedded support devices (ESDs), the selection of link types, and the navigation between visited/unvisited nodes. The experiment results showed the proposed model performed well in identifying learning styles. Link type is the dominant factor and Time shift may not be a major factor in the identification of learning styles. Because of the fast execution property of neural networks and identification of learning styles online, it is possible to incorporate learning styles into online adaptive educational web‐based systems.