Manouselis N., and Sampson D (2002) Dynamic Knowledge Route Selection for Personalised Learning Environments Using Multiple Criteria. In Proc. of the Intelligence and Technology in Educational Applications Workshop (ITEA 2002), International Symposium on Artificial Intelligence and Applications, 20th IASTED International Conference in Applied Informatics (AI 2002), Innsbruck, Austria, February 2002. DYNAMIC KNOWLEDGE ROUTE SELECTION FOR PERSONALISED LEARNING ENVIRONMENTS USING MULTIPLE CRITERIA NIKOS MANOUSELIS and DEMETRIOS SAMPSON Advanced e-Services for the Knowledge Society Research Unit Informatics and Telematics Institute (I.T.I.) Centre for Research and Technology – Hellas (CE.R.T.H.) 1, Kyvernidou Street, Thessaloniki, GR-54639 Greece {nikosm, sampson}@iti.gr ABSTRACT In this paper we deal with the problem of dynamically selecting a knowledge route suitable to individual learner’s needs and profile, through a set of learning resources. We engage parameters of the learner’s cognitive style and create a multi-criteria utility model that evaluates available didactic methods, using initial evaluations upon a set of basic cognitive categories. The proposed methodology is studied within the context of the European KOD project, where intelligent agents providing educational e-content brokerage services to the learners, require methods and tools to dynamically assess the suitability of the available educational resources. KEY WORDS: Personalised e-Learning, Web-based Education 1. INTRODUCTION The rapid evolution of Information and Communication Technologies (ICT) creates numerous opportunities for providing new standards of quality in educational services. It is generally agreed however, that education has not yet realized the full potential of the employment of ICT. This is mainly due to the fact that the traditional mode of instruction (one-to-many lecturing, or one-to-one tutoring), which is adopted in conventional educational technology, cannot fully accommodate the different learning and studying styles, strategies and preferences of diverse learners. In this context, the concept of personalized learning (PL) has emerged, which advocates that learning should not be restricted by time, place or any other barriers, and should be tailored to the continuously modified individual learner’s requirements, abilities, preferences, background knowledge, interests, skills etc [1]. The European IST Project Knowledge-On-Demand (KOD) aims to address needs for the effective and efficient distribution of electronically published learning material, and the provision of personalized learning services in order to favor life-long learning and knowledge transfer experiences through the Web [1]. The idea behind the KOD system is the generation of personal learning paths (referred to as “knowledge routes”) on the published educational material, generated and updated according to the learners’ characteristics (background, interests, skills, etc), which are constantly monitored and profiled. There is a number of R&D efforts worldwide tackling with the engagement of learner’s profile in order to create personalized learning paths. An increasing number of such applications are based on intelligent agents, either strictly concerned with user monitoring and guidance (Steve [2], Turvy [3], Mondrian [4], I-ATCL [5]) or as a technical basis for the organizational structure of the whole system (ALIVE [6], ABITS [7], GIA [8]). The basic difference between these systems and KOD is that, in order to provide personalized services, they depend on the intelligence of the “front-end” agents. On the contrary, KOD introduces the concept of embedding intelligence into the learning packages, so that even “dummy” presentation agents can be able to provide advanced personalization services.