Home > Research > Publications & Outputs > Fad or Future?

Electronic data

  • Lewis_Young_PD_Leake_Lecture_Nov2018_v12_final

    Rights statement: This is an Accepted Manuscript of an article published by Taylor & Francis in Accounting and Business Research on 01 Jun 2019, available online: https://www.tandfonline.com/doi/full/10.1080/00014788.2019.1611730

    Accepted author manuscript, 1.35 MB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

Fad or Future?: Automated Analysis of Financial Text and its Implications for Corporate Reporting

Research output: Contribution to journalJournal articlepeer-review

Published

Standard

Fad or Future? Automated Analysis of Financial Text and its Implications for Corporate Reporting. / Lewis, Craig; Young, Steven.

In: Accounting and Business Research, Vol. 49, No. 5, 29.05.2019, p. 587-615.

Research output: Contribution to journalJournal articlepeer-review

Harvard

APA

Vancouver

Author

Lewis, Craig ; Young, Steven. / Fad or Future? Automated Analysis of Financial Text and its Implications for Corporate Reporting. In: Accounting and Business Research. 2019 ; Vol. 49, No. 5. pp. 587-615.

Bibtex

@article{4368b006923c46c5bd171b74294c4887,
title = "Fad or Future?: Automated Analysis of Financial Text and its Implications for Corporate Reporting",
abstract = "This paper describes the current state of natural language processing (NLP) as it applies to corporate reporting. We document dramatic increases in the quantity of verbal content that are an integral part of company reporting packages as well as the evolution of text analytic approaches that are being employed to analyse this content. We provide intuitive descriptions of the leading analytic approaches that are applied in the academic accounting and finance literatures. This discussion includes key word searches and counts, attribute dictionaries, na{\"i}ve Bayesian classification, cosine similarity, and latent Dirichlet allocation. We also discuss how increasing interest in NLP processing of the corporate reporting package could and should influence financial reporting regulation and note that textual analysis is currently more of an afterthought, if it is even considered. Opportunities for improving the usefulness of NLP processing are discussed as well as possible impediments. ",
author = "Craig Lewis and Steven Young",
note = "This is an Accepted Manuscript of an article published by Taylor & Francis in Accounting and Business Research on 01 Jun 2019, available online: https://www.tandfonline.com/doi/full/10.1080/00014788.2019.1611730",
year = "2019",
month = may,
day = "29",
doi = "10.1080/00014788.2019.1611730",
language = "English",
volume = "49",
pages = "587--615",
journal = "Accounting and Business Research",
issn = "0001-4788",
publisher = "Routledge",
number = "5",

}

RIS

TY - JOUR

T1 - Fad or Future?

T2 - Automated Analysis of Financial Text and its Implications for Corporate Reporting

AU - Lewis, Craig

AU - Young, Steven

N1 - This is an Accepted Manuscript of an article published by Taylor & Francis in Accounting and Business Research on 01 Jun 2019, available online: https://www.tandfonline.com/doi/full/10.1080/00014788.2019.1611730

PY - 2019/5/29

Y1 - 2019/5/29

N2 - This paper describes the current state of natural language processing (NLP) as it applies to corporate reporting. We document dramatic increases in the quantity of verbal content that are an integral part of company reporting packages as well as the evolution of text analytic approaches that are being employed to analyse this content. We provide intuitive descriptions of the leading analytic approaches that are applied in the academic accounting and finance literatures. This discussion includes key word searches and counts, attribute dictionaries, naïve Bayesian classification, cosine similarity, and latent Dirichlet allocation. We also discuss how increasing interest in NLP processing of the corporate reporting package could and should influence financial reporting regulation and note that textual analysis is currently more of an afterthought, if it is even considered. Opportunities for improving the usefulness of NLP processing are discussed as well as possible impediments.

AB - This paper describes the current state of natural language processing (NLP) as it applies to corporate reporting. We document dramatic increases in the quantity of verbal content that are an integral part of company reporting packages as well as the evolution of text analytic approaches that are being employed to analyse this content. We provide intuitive descriptions of the leading analytic approaches that are applied in the academic accounting and finance literatures. This discussion includes key word searches and counts, attribute dictionaries, naïve Bayesian classification, cosine similarity, and latent Dirichlet allocation. We also discuss how increasing interest in NLP processing of the corporate reporting package could and should influence financial reporting regulation and note that textual analysis is currently more of an afterthought, if it is even considered. Opportunities for improving the usefulness of NLP processing are discussed as well as possible impediments.

U2 - 10.1080/00014788.2019.1611730

DO - 10.1080/00014788.2019.1611730

M3 - Journal article

VL - 49

SP - 587

EP - 615

JO - Accounting and Business Research

JF - Accounting and Business Research

SN - 0001-4788

IS - 5

ER -