Title: Semi-automatic financial events discovery based on lexico-semantic patterns

Authors: Jethro Borsje, Frederik Hogenboom, Flavius Frasincar

Addresses: SSC-I, National Agency of Correctional Institutions, The Dutch Ministry of Justice, P.O. Box 850, NL-2800 AW Gouda, The Netherlands. ' Econometric Institute, Erasmus University Rotterdam, P.O. Box 1738, NL-3000 DR Rotterdam, The Netherlands. ' Econometric Institute, Erasmus University Rotterdam, P.O. Box 1738, NL-3000 DR Rotterdam, The Netherlands

Abstract: Due to the market sensitivity to emerging news, investors on financial markets need to continuously monitor financial events when deciding on buying and selling equities. We propose the use of lexico-semantic patterns for financial event extraction from RSS news feeds. These patterns use financial ontologies, leveraging the commonly used lexico-syntactic patterns to a higher abstraction level, thereby enabling lexico-semantic patterns to identify more and more precisely events than lexico-syntactic patterns from text. We have developed rules based on lexico-semantic patterns used to find events, and semantic actions that allow for updating the domain ontology with the effects of the discovered events. Both the lexico-semantic patterns and the semantic actions make use of the triple paradigm that fosters their easy construction and understanding by the user. Based on precision, recall, and F₁ measures, we show the effectiveness of the proposed approach.

Keywords: update actions; ontologies; financial events; lexico-semantic patterns; market sensitivity; emerging news; financial markets; equities; financial event extraction; RSS news feeds.

DOI: 10.1504/IJWET.2010.038242

International Journal of Web Engineering and Technology, 2010 Vol.6 No.2, pp.115 - 140

Published online: 24 Jan 2011 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article