Combining Machine Learning and Semantic Features in the Classification of Corporate Disclosures

Evert S, Heinrich P, Henselmann K, Rabenstein U, Scherr E, Schröder L (2017)

Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2017

Publisher: Stockholm University

City/Town: Stockholm

Pages Range: 47 - 62

Conference Proceedings Title: Proceedings of the Workshop on Logic and Algorithms in Computational Linguistics 2017 (LACompLing2017)

Event location: Stockholm SE

URI: http://su.diva-portal.org/smash/get/diva2:1140018/FULLTEXT03.pdf

Abstract

We investigate an approach of improving statistical text classification by combining machine learners with an ontology-based identification of domain-specific topic categories. We apply this approach to ad hoc disclosures by public companies. This form of obligatory publicity concerns all information that might affect the stock price; relevant topic categories are governed by stringent regulations. Our goal is to classify disclosures according to their effect on stock prices (negative, neutral, positive). In the feasibility study reported here, we combine natural language parsing with a formal background ontology to recognize disclosures concerning a particular topic, viz. retirement of key personnel. The semantic analysis identifies such disclosures with high precision and recall. We then demonstrate that machine learners benefit from the additional ontology-based information in different prediction tasks.

Authors with CRIS profile

Stephanie Evert Lehrstuhl für Korpus- und Computerlinguistik Philipp Heinrich Lehrstuhl für Korpus- und Computerlinguistik Klaus Henselmann Lehrstuhl für Betriebswirtschaftslehre, insbesondere Rechnungswesen und Prüfungswesen Ulrich Rabenstein Lehrstuhl für Informatik 8 (Theoretische Informatik) Elisabeth Scherr Juniorprofessur für Wirtschaftsprüfung mit dem Schwerpunkt digitale Datenanalyse Lutz Schröder Lehrstuhl für Informatik 8 (Theoretische Informatik)

Related research project(s)

Reconstructing Arguments from Noisy Text (DFG Priority Programme 1999: RATIO) (RANT) Jan. 1, 2018 - Dec. 31, 2020 Probabilistische Beschreibungslogik als Fragment der Probabilistischen Logik Erster Stufe (ProbDL) April 1, 2011 - April 1, 2014

How to cite

APA:

Evert, S., Heinrich, P., Henselmann, K., Rabenstein, U., Scherr, E., & Schröder, L. (2017). Combining Machine Learning and Semantic Features in the Classification of Corporate Disclosures. In Loukanova R, Liefke K (Eds.), Proceedings of the Workshop on Logic and Algorithms in Computational Linguistics 2017 (LACompLing2017) (pp. 47 - 62). Stockholm, SE: Stockholm: Stockholm University.

MLA:

Evert, Stephanie, et al. "Combining Machine Learning and Semantic Features in the Classification of Corporate Disclosures." Proceedings of the Logic and Algorithms in Computational Linguistics 2017 (LACompLing2017), Stockholm Ed. Loukanova R, Liefke K, Stockholm: Stockholm University, 2017. 47 - 62.

BibTeX: Download