INTECIN   20395
INSTITUTO DE TECNOLOGIAS Y CIENCIAS DE LA INGENIERIA "HILARIO FERNANDEZ LONG"
Unidad Ejecutora - UE
capítulos de libros
Título:
Scalable Faceted Ranking in Tagging Systems
Autor/es:
JOSÉ I. ORLICKI, J. IGNACIO ALVAREZ-HAMELIN AND PABLO I. FIERENS
Libro:
Web Information Systems and Technologies - 5th International Conference, WEBIST 2009, Revised Selected Papers
Editorial:
Springer
Referencias:
Año: 2009;
Resumen:
Nowadays, web collaborative tagging systems which allow users to upload, comment on and recommend contents, are growing. Such systems can be represented as graphs where nodes correspond to users and tagged-links to recommendations. In this paper we analyze the problem of computing a ranking of users with respect to a facet described as a set of tags. A straightforward solution is to compute a PageRank-like algorithm on a facet-related graph, but it is not feasible for online computation. We propose an alternative: (i)  a ranking for each tag is computed offline on the basis of tag-related subgraphs; (ii) a faceted order is generated online by merging rankings corresponding to all the tags in the facet. Based on the graph analysis of YouTube and Flickr, we show that step (i) is scalable. We also present efficient algorithms for step (ii), which are evaluated by comparing their results with two gold standards.