Clustering semantics for hypermedia presentation

Semantic annotations of media repositories make relationships among the stored media and relevant concepts explicit. However, these relationships and the media they join are not directly presentable as hypermedia. Previous work shows how clustering over the annotations in the repositories can determine hypermedia presentation structure. Here we explore the application of different clustering techniques to generating hypermedia interfaces to media archives. This paper also describes the effect of each type of clustering on the end user's experience. We then generalize and unify these techniques with the use of proximity measures in further improving generated presentation structure