Automated semantic elaboration of web site information architecture

Structuring of the content is an important step in web site design, affecting greatly navigability and the overall user experience. Automated support of this task is the object of this paper. AutoCardSorter, a computational tool that supports clustering of the web pages of a site, is introduced. The proposed tool-based methodology uses semantic similarity measures, such as latent semantic analysis, and hierarchical clustering algorithms, in order to suggest suitable information navigation schemes. In the paper, after introducing AutoCardSorter design and functionality, three independent studies are discussed. The studies, that were conducted in order to validate the proposal, compared the proposed method with the established card-sorting approach, in different domains. It was found that substantial gain in effectiveness was achieved without expense in the quality of results, therefore, reducing the required time and human resources.