Identification and Ranking of Event-Specific Entity-Centric Informative Content from Twitter

摘要: Twitter has become the leading platform for mining information related to real-life events. A large amount of shared content in are non-informative spams and informal personal updates. Thus, it is necessary identify rank informative event-specific from Twitter. Moreover, tweets containing about named entities (like person, place, organization, etc.) occurring context an event, generates interest aids gaining useful insights. In this paper, we develop a novel generic model based on principle mutual reinforcement, representing identifying event-specific, as well entity-centric An algorithm proposed that ranks terms by leveraging semantics relationships between different units model.