Automatic Metadata Generation using Associative Networks

dc.creatorRodriguez, Marko A.
dc.creatorBollen, Johan
dc.creatorVan de Sompel, Herbert
dc.date2008-06-30
dc.date2009-03-07
dc.date.accessioned2026-07-07T12:49:28Z
dc.date.available2026-07-07T12:49:28Z
dc.descriptionIn spite of its tremendous value, metadata is generally sparse and incomplete, thereby hampering the effectiveness of digital information services. Many of the existing mechanisms for the automated creation of metadata rely primarily on content analysis which can be costly and inefficient. The automatic metadata generation system proposed in this article leverages resource relationships generated from existing metadata as a medium for propagation from metadata-rich to metadata-poor resources. Because of its independence from content analysis, it can be applied to a wide variety of resource media types and is shown to be computationally inexpensive. The proposed method operates through two distinct phases. Occurrence and co-occurrence algorithms first generate an associative network of repository resources leveraging existing repository metadata. Second, using the associative network as a substrate, metadata associated with metadata-rich resources is propagated to metadata-poor resources by means of a discrete-form spreading activation algorithm. This article discusses the general framework for building associative networks, an algorithm for disseminating metadata through such networks, and the results of an experiment and validation of the proposed method using a standard bibliographic dataset.
dc.identifierhttps://arxiv.org/abs/0807.0023
dc.identifierhttp://arxiv.org/abs/0807.0023
dc.identifierACM Transactions on Information Systems, volume 27, number 2, pages 1-20, ISSN: 1046-8188, ACM Press, February 2009
dc.identifierdoi:10.1145/1462198.1462199
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/222412
dc.subjectInformation Retrieval
dc.subjectDigital Libraries
dc.subjectH.3.1; H.3.7
dc.titleAutomatic Metadata Generation using Associative Networks
dc.typetext

Files

Collections