Towards a Framework for Trusting the Automated Learning of Social Ontologies

Abstract

Automatically learned social ontologies are products of social fermentation between users that belong in communities of common interests (CoI), in open, collaborative and communicative environments. In such a setting, social fermentation ensures automatic encapsulation of agreement and trust of the shared knowledge of participating stakeholders during an ontology learning process. The paper discusses key issues for trusting the automated learning of social ontologies from social data and furthermore it presents a framework that aims to capture the interlinking of agreement, trust and the learned domain conceptualizations that are extracted from such a type of data. The motivation behind this work is an effort towards supporting the design of new methods for learning trusted ontologies from social content i.e. methods that aim to learn not only the domain conceptualizations but also the degree that agents (software and human) may trust them or not.