In this paper, we study user modeling on Twitter and investigate the interplay between personal interests and public trends. To generate semantically meaningful user profiles, we present a framework that allows us to enrich the semantics of individual Twitter messages and features user modeling as well as trend modeling strategies. These profiles can be re-used in other applications for (trend-aware) personalization. Given a large Twitter dataset, we analyze the characteristics of user and trend profiles and evaluate the quality of the profiles in the context of a personalized news recommendation system. We show that personal interests are more important for the recommendation process than public trends and that by combining both types of profiles we can further improve recommendation quality.

With the enormous and still growing amount of data and user interaction on the Web, it becomes more and more necessary for data consumers to be able to assess the trustworthiness of data on the Web. In this paper, we present a framework for trust establishment and assessment on the Web of Data. Different from many approaches that build trust metrics within networks of people, we propose a model to represent the trust in concrete pieces of web data for a specific consumer, in which also the context is considered. Further more, we provide three strategies for trust assessment based on the principles of Linked Data, to overcome the shortcomings of the conventional web of documents: i.e. the lack of semantics and interlinking.