Enhancing Ontology Alignment Recommendation by Exploring Emergent Social Networks
Virgínia Nascimento, Alda Canito, M. Viamonte, Nuno Silva · 2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology · 2012
In electronic commerce the diversity of the involved actors can lead to different conceptualizations of their needs and capabilities giving rise to semantic incompatibilities that might hamper negotiations and the fulfilling of satisfactory transactions. AEMOS is an agent-based electronic commerce platform that provides ontology mapping services, including the recommendation of possible ontology alignments between the negotiation agents' conceptualizations/ontologies. In this paper we introduce a new component that, improves the ontology alignment recommendations and support the agents' decisions about which alignments to select, based on the information collected throughout the market and by exploring social network analysis techniques. We illustrate how the collaboration between the different agents can be helpful in improving this component's performance, and how its support reflects in the efficiency of the negotiation process.