Paul De Bra

AHAM: a Dexter-based reference model for adaptive hypermedia

Hypermedia applications offer users the impression that there are many meaningful ways to navigate through a large body of information nodes. This rich link structure not only creates orientation problems, it may also be a source of comprehension problems when users follow paths through the information which the author did not foresee. Adaptive techniques have been used by a number of researchers [1, 2, 4, 5, 6, 7, 8, 9, 10, 17, 19, 20, 22] in an attempt to offer guidance through and orientation support for rich link structures. The majority of these adaptive hypermedia systems (AHS) have been used in educational applications. The terminology used in this paper also has an educational “flavor”. However, there are some adaptive on-line information systems (or “kiosk”systems), adaptive information retrieval systems, and other adaptive hypermedia applications. In this paper we describe a reference model for adaptive hypermedia applications, called AHAM, which encompasses most features supported by adaptive systems that exist today or that are being developed (and have been published about). Our description of AHS is based on the Dexter model [15, 16], a widely used reference model for hypermedia. The description is kept somewhat informal in order to be able to explain AHAM rather than formally specify it. AHAM augments Dexter with features for doing adaptation based on a user model which persists beyond the duration of a session. Key aspects in AHAM are: Paul De Bra is also affiliated with the University of Antwerp, Belgium, and with the “Centrum voor Wiskunde en Informatica” (CWI) in Amsterdam. yGeert-Jan Houben is also affiliated with the University of Antwerp, Belgium, and with Origin in Eindhoven. The adaptation is based on a domain model, a user model and a teaching model which consists of pedagogical rules. We give a formal definition of each of these (sub)models (but only describe the pedagogical rules informally throughexamples). We distinguish the notions of concept, page and fragment. In some AHS these notions are confused. We provide a formalism which lets authors write pedagogical rules (about concepts) in such a way that they can be applied automatically. We illustrate various aspects of AHAM by means of some features of some well-known AHS [6, 10].

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.

Authoring of learning styles in adaptive hypermedia: problems and solutions

Learning styles, as well as the best ways of responding with corresponding instructional strategies, have been intensively studied in the classical educational (classroom) setting. There is much less research of application of learning styles in the new educational space, created by the Web. Moreover, authoring applications are scarce, and they do not provide explicit choices and creation of instructional strategies for specific learning styles. The main objective of the research described in this paper is to provide the authors with a tool which will allow them to incorporate different learning styles in their adaptive educational hypermedia applications. In this way, we are creating a semantically significant interface between classical learning styles and instructional strategies and the modern field of adaptive educational hypermedia.

Design issues for general-purpose adaptive hypermedia systems

A hypermedia application offers its users much freedom to navigate through a large hyperspace. For authors finding a good compromise between offering navigational freedom and offering guidance is difficult, especially in applications that target a broad audience. Adaptive hypermedia (AH) offers (automatically generated) personalized content and navigation support, so the choice between freedom and guidance can be made on an individual basis. Many adaptive hypermedia systems (AHS) are tightly integrated with one specific application. In this paper we study design issues for general-purpose adaptive hypermedia systems, built according to an application-independent architecture. We use the Dexter-based AHAM reference model for adaptive hypermedia [7] to describe the functionality of such systems at the conceptual level. We concentrate on the architecture and behavior of a general-purpose adaptive engine. Such an engine performs adaptation and updates the user model according to a set of adaptation rules specified in an adaptation model. In our study of the behavior of such a system we concentrate on the issues of termination and confluence, which are important to detect potential problems in an adaptive hypermedia application. We draw parallels with static rule analysis in active database systems [1,2]. By using common properties of AIIS we are able to obtain more precise (less conservative) results for AHS than for active databases in general, especially for the problem of termination.

Discovering prediction rules in AHA! courses

In this paper we are going to show how to discover interesting prediction rules from student usage information to improve adaptive web courses. We have used AHA! to make courses that adapt both the presentation and the navigation depending on the level of knowledge that each particular student has. We have performed several modifications in AHA! to specialize it and power it in the educational area. Our objective is to discover relations between all the picked-up usage data (reading times, difficulty levels and test results) from student executions and show the most interesting to the teacher so that he can carry out the appropriate modifications in the course to improve it.

An extensible data model for hyperdocuments

We present an extensible data model for hyperdocuments. It is intended to serve as the basis for integrating hypermedia systems with other information sources, such as object-oriented database management systems, information retrieval systems, and engineering CAD tools. Hyperdocuments are described by means of a small number of powerful constructs that integrate their structural and behavioral aspects. The different instantiations and combinations of these constructs yield an open class of hyperdocuments. Nodes, anchors, and links are all considered first-class objects and modeling constructs are applicable to all of them. These constructs permit a description of the multiple levels of functionality of an object within a hyperdocument, and the packaging of the different views of an object. Composite objects range over an extensible collection of structures including networks, sets, time-lines, and three-dimensional space CAD models.

Personalized links recommendation based on data mining in adaptive educational hypermedia systems

In this paper, we describe a personalized recommender system that uses web mining techniques for recommending a student which (next) links to visit within an adaptable educational hypermedia system. We present a specific mining tool and a recommender engine that we have integrated in the AHA! system in order to help the teacher to carry out the whole web mining process. We report on several experiments with real data in order to show the suitability of using both clustering and sequential pattern mining algorithms together for discovering personalized recommendation links.

An authoring tool for building both mobile adaptable tests and web-based adaptive or classic tests

This paper describes Test Editor, an authoring tool for building both mobile adaptable tests and web-based adaptive or classic tests. This tool facilitates the development and maintenance of different types of XML-based multiple-choice tests for using in web-based education systems and wireless devices. We have integrated Test Editor into the AHA! system, but it can be used in other web-based systems as well. We have also created several test execution engines in Java language in order to be executed in different devices such as PC and mobile phones. In order to test them, we have carried out two experiments with students to determine the usefulness of adaptive tests and mobile tests.

GRAPPLE: Learning Management Systems Meet Adaptive Learning Environments

Learning Management Systems (LMSs) are used in many (educational) institutes to manage the learning process. Adaptive Learning Environments (ALEs) offer support for the learning process through adaptive guidance and perhaps also personalized learning material (content). GRAPPLE offers a new infrastructure that brings both together. This is done through single sign-on, a common User Model Framework and an (asynchronous) event bus that coordinates the communication between the other components. Authors can create structured course material and define the adaptation through a graphical interface, and a flexible and very extensible adaptation engine offers almost any type of presentation and adaptation an author might want. This chapter reports on early experience with the GRAPPLE environment, for teaching and for learning.

Bisimulation reduction of big graphs on mapreduce

Computing the bisimulation partition of a graph is a fundamental problem which plays a key role in a wide range of basic applications. Intuitively, two nodes in a graph are bisimilar if they share basic structural properties such as labeling and neighborhood topology. In data management, reducing a graph under bisimulation equivalence is a crucial step, e.g., for indexing the graph for efficient query processing. Often, graphs of interest in the real world are massive; examples include social networks and linked open data. For analytics on such graphs, it is becoming increasingly infeasible to rely on in-memory or even I/O-efficient solutions. Hence, a trend in Big Data analytics is the use of distributed computing frameworks such as MapReduce. While there are both internal and external memory solutions for efficiently computing bisimulation, there is, to our knowledge, no effective MapReduce-based solution for bisimulation. Motivated by these observations we propose in this paper the first efficient MapReduce-based algorithm for computing the bisimulation partition of massive graphs. We also detail several optimizations for handling the data skew which often arises in real-world graphs. The results of an extensive empirical study are presented which demonstrate the effectiveness and scalability of our solution.