Semantics-Based Financial Event Detection

Breaking news on economic events - e.g., acquisitions, profit announcements, and stock splits - has a substantial impact on financial markets. Hence, automatically identifying events in news items accurately and timely is of great importance. In this paper 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 additionally, developed new ones, e.g., an Ontology Gazetteer and a Word Sense Disambiguator.