An innovative user-attentive framework for supporting real-time detection and mining of streaming microblog posts

In this paper, we present a modular system capable of catching the attention of a new user, to detect in real-time events and emotions related to them in a stream of microblog posts. The system is capable of making social sensing and exploiting the information arising on the Internet through user-generated contents, and it is equipped with a conversational engine that manages the interaction with the human user. The whole approach can be applied either by a human user or a robot, which remains a future application to be further improved in the context of our proposed system.