Task-Centered Selection of Learning Material

Abstract

Learning needs in complex working environments call for e-learning systems which intelligently support the learner. As everyday tasks keep getting more and more complex employees consistently have to update their knowledge and adapt to new processes. As a consequence a lot of time has to be spent on research for appropriate help and learning material. The aim is to decrease the time the user has to spend on his hunt for information and to offer him the needed help and learning material in an on-demand manner. We present a new approach for semantic retrieval of learning units taking the working context into account. Basis is an ontology with attached binding weights. A context-aware ranking of help and learning material is generated with a semantic spreading activation algorithm. The gained semantic search results match to the learner’s actual situation better than e.g. a pure full-text search, because the underlying ontology-based retrieval is aware of relations in the search domain and uses this knowledge in a way aligned to the learning process as well as to the specific domain. The results are shown in a prototype implementation of an assistance and learning system for Synthetic Aperture Radar (SAR) image interpretation. This work is based on [15] and is extended by new aspects to the retrieval method and a comparison with a full-text search engine.