Towards Adaptive Generation of Faded Examples

Abstract. Faded examples have been investigated in pedagogical psychology. The experiments suggest that a learner can benefit from faded examples. For these experiments a few examples were faded manually. For realistic applications, however, it makes more sense to generate several variants of an exercise by fading a worked example and to do it automatically. For the automatic generation, a suitable knowledge representation of examples and exercises is required which we describe in the paper. Moreover, a user-adaptive system such as ActiveMath can select or dynamically produce faded example and present it to the student in response to her learning activities and adapted to her goals, capabilities, previous learning experience, etc. The structures and metadata in the knowledge representation of the examples are the basis for such an adaptation. In particular, it allows to fade a variety of parts of the example rather than only solution steps.

• Type: Conference
• Year: 2004
• Where: ITS
• Authors: Erica Melis, Georgi Goguadze
• Keywords: Artificial Intelligence, Faded Example, ITS 2004, Knowledge Representation, Suitable Knowledge Representation