Ontological User Profiling and Language Modeling for Personalized Information Services

With the explosive growth of the information and services deployed to the Web, there is a pressing need to develop an effective service for personalized services discovery and recommendation. Despite personalized services discovery methods have been studied by researchers before, few attempts have been made to explore ontological user profiling and probabilistic language modeling approach for service contextualization and service ranking. This paper makes a novel contribution in terms of developing an agent and ontology based user profiling mechanism to improve the service discovery processes. In particular, a novel probabilistic language modeling approach is developed to conduct service contextualization and service ranking. Our initial experimental results show that the proposed service personalization approach is promising when compared with a baseline system.