E-Learning and Semantic Technologies

Introduction

Traditional teaching and learning methods have had to adapt to keep up with Information and Communication Technologies (ICTs) in modern society. E-learning stands for all forms of Web-based learning and uses computer and computer networks to create, store, deliver, manage and support online learning courses to anyone, anytime and anywhere. It provides a configurable infrastructure that can integrate learning materials, tools, and services into a single solution to create and deliver training or educational materials quickly, effectively, and economically.

Recently, emerging Semantic Web technologies have changed the focus of e-learning systems from task-based approaches to knowledge-intensive ones. The Semantic Web is a W3C initiative and according to Berners-Lee et al. (2001) comprises “an extension of the current Web in which information is given well-defined meaning, better enabling computers and people to work in cooperation”. The capability of the Semantic Web to add meaning to information, stored in such way that it can be searched and processed, as well as recent advances in Semantic Web-based technologies provide the mechanisms for semantic knowledge representation, exchange and collaboration of e-learning applications (Anderson & Whitelock, 2004).

Semantic e-learning is the “e-learning based on the Semantic Web technologies that can easily provide learning materials in a common format and therefore enhance personalised learning” (Cao & Zhang, 2006). In this context, e-learning systems have the potential to develop descriptions of their processes, as well as rules in order to create content-based and logic-driven information and knowledge value.

The aim of this article is to define Semantic e-learning, review the literature and all these foundations upon which it is envisioned and demonstrate its close relation with development of Semantic Web technologies. Moreover, we present the directions that support the vision of Semantic e-learning, illustrate the future trends and discuss the open issues in the field.

Background

In the majority of past e-learning systems the courses and the educational materials were not dynamic enough, provided a rather restricted feature set or presented complicated structuring and consequently could not respond effectively to the needs and competencies of the learners, resulting in poor experiences. An answer to this problem that comprises also the current challenge for Web-based learning systems is their enhancement by the integration of adaptive features that allow for the delivery of personalized learning (Brusilovsky, 2001). These advanced e-learning applications provide high quality content, efficient structuring, and full support for the varied tasks of all the user profiles participating in a typical distance learning scenario. Specifically, depending on the knowledge background of the learner, his strengths and weaknesses, as well as the preferred learning style and the progress made so far, the system decides what and in which way the content should be presented next. Possible parameters are different learning paths through the content, different ways of presentation of the same content (e.g. with or without audio) or offering a different set of functions which the user interface of the learning system provides to reduce complexity.

To achieve this, methods and techniques from various scientific domains and application areas are used. The most well-known are Data Mining, Web Mining, Knowledge Discovery, User Modelling, User Profiling, Artificial Intelligence and Agent Technologies, etc. Especially, Web Mining is defined as the use of Data Mining techniques for discovering and extracting information from web documents and services and is distinguished as Web Content, Structure or Usage Mining depending on which part of the Web is mined (Kosala & Blockeel, 2000). In the majority of cases, e-learning applications base personalization on Web Usage Mining, which undertakes the task of gathering and extracting all data required for constructing and maintaining learners’ profiles based on the behaviour of each user as recorded in server logs (Markellou et al., 2004).