Detecting economic events using a semantics-based pipeline
In today's information-driven global economy, breaking news on economic events such as acquisitions and stock splits has a substantial impact on the financial markets. Therefore, it is important to be able to automatically identify events in news items accurately and in a timely manner. For this purpose, one has to be able to mine a wide variety of heterogeneous sources of unstructured data to extract knowledge that is useful for guiding decision making processes. We propose a Semantics-based Pipeline for Economic Event Detection (SPEED), which aims at extracting financial events from news articles and annotating these events with meta-data, while retaining a speed that is high enough to make real-time use possible. In our pipeline implementation, we have reused some of the components of an existing framework and developed new ones, such as an Ontology Gazetteer and a Word Sense Disambiguator.