Work

Word Embeddings-Based Uncertainty Detection in Financial Disclosures

Year: 2018

Type: conference-paper

Abstract: In this paper, we use NLP techniques to detect linguistic uncertainty in financial disclosures.Leveraging generaldomain and domain-specific word embedding models, we automatically expand an existing dictionary of uncertainty triggers.We furthermore examine how an expert filtering affects the quality of such an expansion.We show that the dictionary expansions significantly improve regressions on stock return volatility.Lastly, we prove that the expansions significantly boost the automatic detection of uncertain sentences.

DOI: 10.18653/v1/w18-3104

Authors: Christoph Kilian Theil, Sanja Štajner, Heiner Stuckenschmidt

Institution: University of Mannheim

Language: English

Topic: Stock Market Forecasting Methods

Subfield: Management Science and Operations Research

Field: Decision Sciences

Domain: Social Sciences

Open Access status: gold

Funders: Deutsche Forschungsgemeinschaft, Universität Mannheim

Awards: G138831034, G1450655456, G2228243831

OpenAlex ID: W2951416252