Identifying Firm-Specific Risk Statements in News Articles

Abstract

Textual data are an important information source for risk management for business organizations. To effectively identify, extract, and analyze risk-related statements in textual data, these processes need to be automated. We developed an annotation framework for firm-specific risk statements guided by previous economic, managerial, linguistic, and natural language processing research. A manual annotation study using news articles from the Wall Street Journal was conducted to verify the framework. We designed and constructed an automated risk identification system based on the annotation framework. The evaluation using manually annotated risk statements in news articles showed promising results for automated risk identification.