A Computational Model of Trust Based on Message Content and Source
Résumé
We propose a general possibilistic framework to determine the a-gent's trust degree in a source, starting from the content of the messages such source provides and based on the beliefs of the agent about the capability of the source to provide " useful information ". The result is a framework with unique characteristics, which combines experience-, reputation-, content-, and category-based models of trust in one coherent computational model.
Domaines
Intelligence artificielle [cs.AI]Origine | Fichiers éditeurs autorisés sur une archive ouverte |
---|
Loading...