Performance Evaluation of Decision-Based Content Selection Approaches in Adaptive Educational Hypermedia Systems

Abstract

Adaptive content selection is recognized as a challenging research issue in adaptive educational hypermedia systems (AEHS). In order to adaptively select learning objects (LO) in AEHS, the definition of adaptation behavior, referred to as Adaptation Model (AM), is required. Several efforts have been reported in literature aiming to support the AM design by providing AEHS designers with either guidance for the direct definition of adaptation rules, or semi-automated mechanisms which generate the AM via the implicit definition of such rules. The goal of the semi-automated, decision-based approaches is to generate a continuous decision function that estimates the desired AEHS response, aiming to overcome the problems of insufficiency and/or inconsistency in the defined adaptation rule sets. Although such approaches bare the potential to provide efficient AM, they still miss a commonly accepted framework for evaluating their performance. In this chapter, we discuss a set of performance evaluation metrics that have been proposed by the literature for validating the use of decision-based approaches in adaptive LO selection in AEHS and assess the use of these metrics in the case of our proposed statistical method for estimating the desired AEHS response.KeywordsAdaptation RuleMedia SpaceImplicit DefinitionDirect DefinitionLearner ProfileThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.