A WOWA-based Aggregation Technique on Trust Values Connected to Metadata

Ernesto Damiani, Sabrina De Capitani di Vimercati, Pierangela Samarati, Marco Viviani

Research output: Contribution to journalArticlepeer-review

37 Scopus citations

Abstract

Metadata produced by members of a diverse community of peers tend to contain low-quality or even mutually inconsistent assertions. Trust values computed on the basis of users' feedback can improve metadata quality and reduce inconsistency, eliminating untrustworthy assertions. In this paper, we describe an approach to metadata creation and improvement, where community members express their opinions on the trustworthiness of each assertion. Our technique aggregates individual trustworthiness values to obtain a community-wide assessment of each assertion. We then apply a global trustworthiness threshold to eliminate some assertions to reduce the metadatabase's overall inconsistency.

Original languageBritish English
Pages (from-to)131-142
Number of pages12
JournalElectronic Notes in Theoretical Computer Science
Volume157
Issue number3
DOIs
StatePublished - 25 May 2006

Keywords

  • community-wide trust
  • Metadata assertions
  • trustworthiness

Fingerprint

Dive into the research topics of 'A WOWA-based Aggregation Technique on Trust Values Connected to Metadata'. Together they form a unique fingerprint.

Cite this