A flexible approach for context-aware service selection in agent-mediated e-commerce

Abstract

In this dissertation, we examine the problem of service selection in an e‐commerce setting where consumer agents cooperate to identify providers that would satisfy their service needs the most. There are three major challenges related to service selection: (i) representing consumers' past dealings with providers, (ii) handling deceptive information and (iii) managing evolution of consumers' service needs and semantics. Previous approaches represent consumers' past dealings with providers only as ratings. Even though the context is crucial for interpreting the ratings correctly, ratings do not contain any contextual information explicitly. A rating merely represents subjective opinion of a consumer about a provider. Because, the satisfaction criteria and the expectations of the rater are unknown, it is almost impossible to make sense of a rating. In this dissertation, consumers’ experiences with providers are represented with an ontology that can semantically capture the requested service and the received service in detail. When a consumer decides to share its experiences with a second consumer, the receiving consumer evaluates the experience using its own context and satisfaction criteria. By sharing experiences rather than ratings, the consumers can model providers more accurately and thus can select providers that are better suited for their needs. The proposed service selection approach in this dissertation is flexible enough to enable consumers to evolve their service semantics over time; context‐aware and consumer‐oriented to enable consumers to use their own satisfaction criteria and context during service selection; and robust to deception to lead satisfactory service selections even in highly deceptive environments.