Current Slide

Small screen detected. You are viewing the mobile version of SlideWiki. If you wish to edit slides you will need to use a larger device.

Trustworthiness Metrics 1

  • T1: computing statement trust values based on:
    • provenance information which can be either unknown or a value in the interval [−1,1] where 1: absolute belief, −1: absolute disbelief and 0: lack of belief/disbelief [18,28]
    • opinion-based method, which use trust annotations made by several individuals [23,28]
    • provenance information and trust annotation in Semantic Web-based social-networks [24]
    • annotating triples with provenance data and usage of provenance history to evaluate the trustworthiness of facts [16]
  • T2: using annotations for data to encode two facets of information:
    • blacklists (indicates that the referent data is known to be harmful) [12] and
    • authority (a boolean value which uses the Linked Data principles to conservatively determine whether or not information can be trusted) [12]
  • T3: using trust ontologies that assigns trust values that can be transferred from known to unknown data [33] using:
    • content-based methods (from content or rules) and
    • metadata-based methods (based on reputation assignments, user ratings, and provenance, rather than the content itself)


Speaker notes:

Content Tools

Sources

There are currently no sources for this slide.