Abstract:

Trust and reputation allow agents to make informed decisions about potential interactions. Trust in an agent is derived from direct experience with that agent, while reputation is determined by the experiences reported by other witness agents with potentially differing viewpoints. These experiences can be represented in tuples describing the situation and outcomes of the interaction, or depicted in detail as is possible with provenance records. These experiences are typically aggregated in a trust and reputation model, of which there are several types that focus on different aspects. Such aspects include handling subjective perspectives of witnesses, dishonesty, or assessing the reputation of new agents. This talk distills reputation into its fundamental aspects, discussing first how trust and experiences and reputation information is represented and second how it is disseminated among agents. A unifying abstraction for reputation systems is presented, along example instantiations of models found in the literature. Finally, the abstraction is instantiated using machine learning approaches to pave the way for in depth analysis of provenance records for trust and reputation assessments.