SOAF: semantic indexing system based on collaborative tagging

The creation of Learning Objects and learning assets for e-Learning, as well as the development of more and more extensive repositories, is actually a generalized practice in all educational organizations. However, automatic tools for searching and locating learning content in these repositories based on semantic tags are not yet effective. This article proposes a system architecture called SOAF for the semantic indexing of Learning Objects from a repository. It combines automatic techniques of information retrieval with collaborative tagging of documents made by users. In this way, the metadata of the Learning Objects provides real meaning derived from the learning practice in user communities able to share their experiences through specific annotation of the learning content, which will identify each Learning Object and will improve its reusability in new learning contexts. Keywords: Semantic indexing, emergent semantic, semantic gap, Learning Objects, users annotations, social learning, social tags, folksonomy.