Event Mining over Distributed Text Streams

This research presents a new set of techniques to deal with event mining from different text sources, a complex set of NLP tasks which aim to extract events of interest and their components including authors, targets, locations, and event categories. Our focus is on distributed text streams, such as tweets from different news agencies, in order to accurately retrieve events and its components by combining such sources in different ways using text stream mining. Therefore this research project aims to fill the gap between batch event mining, text stream mining and distributed data mining which have been used separately to address related learning tasks. We propose a multi-task and multi-stream mining approach to combine information from multiple text streams to accurately extract and categorise events under the assumptions of stream mining. Our approach also combines ontology matching to boost accuracy under imbalanced distributions. In addition, we plan to address two relatively unexplored event mining tasks: event coreference and event synthesis. Preliminary results show the appropriateness of our proposal, which is giving an increase of around 20% on macro prequential metrics for the event classification task.