Twitter as a personalizable information service

Abstract

Twitter is a free social networking microblogging service that allows registeredmembers to broadcast, in real-time, short posts called tweets. Twittermembers can broadcast tweets and follow other users’ tweets by using multiple devices, making this information system one of the fastest in theworld. In this chapter, we leverage this characteristic to introduce a novel topic-detection method aimed at informing, in real-time, a specific user about the most emerging arguments expressed by the network around his/her domain interests. With this goal, we aim at formalizing the information spread over the network by studying the topology of the network and by modeling the implicit and explicit connections among the users. Then, we propose an innovative term aging model, based on a biological metaphor, to retrieve the freshest arguments of discussion, represented through a minimal set of terms, expressed by the community within the foci of interest of a specific user. We finally test the proposed model through various experiments and user studies.