Abstract
AbstractWe critically assess mainstream accounting and finance research applying methods from computational linguistics (CL) to study financial discourse. We also review common themes and innovations in the literature and assess the incremental contributions of studies applying CL methods over manual content analysis. Key conclusions emerging from our analysis are: (a) accounting and finance research is behind the curve in terms of CL methods generally and word sense disambiguation in particular; (b) implementation issues mean the proposed benefits of CL are often less pronounced than proponents suggest; (c) structural issues limit practical relevance; and (d) CL methods and high quality manual analysis represent complementary approaches to analyzing financial discourse. We describe four CL tools that have yet to gain traction in mainstream AF research but which we believe offer promising ways to enhance the study of meaning in financial discourse. The four tools are named entity recognition (NER), summarization, semantics and corpus linguistics.
Highlights
Information is the lifeblood of financial markets and the amount of data available to decision-makers is increasing exponentially
Intrinsic evaluation involves understanding the performance of a specific processing tool. It can be distinguished from extrinsic evaluation which seeks to determine how well a specific processing tool is performing as part of an entire language technology system
We conclude that the main weakness of prior work is its continued reliance on simple bag-of-words content analysis methods that fail to reflect context and disambiguate meaning
Summary
Information is the lifeblood of financial markets and the amount of data available to decision-makers is increasing exponentially. Bank of England (2015) estimates that 90% of global information has been created during the last decade, the vast majority of which is unstructured data (e.g., free-form text).. Dyer et al (2017) find a 113% increase in the median length of U.S registrants’ 10-K annual reports over the period 1996-2013 and Lewis and. Young (2018) report similar results for U.K. annual reports. The volume of unstructured financial data exceeds the capacity of humans to process the content manually. Users of financial market data are turning increasingly to computational linguistics to assist with the task of analyzing large volumes of unstructured data.. Users of financial market data are turning increasingly to computational linguistics to assist with the task of analyzing large volumes of unstructured data. Academic research in accounting and finance is mirroring this trend
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call