Identification of fraudulent financial statements using linguistic credibility analysis

Sean L. Humpherys; Kevin C. Moffitt; Mary B. Burns; Judee K. Burgoon; William F. Felix

doi:10.1016/j.dss.2010.08.009

Identification of fraudulent financial statements using linguistic credibility analysis

Sean L. Humpherys, Kevin C. Moffitt, Mary B. Burns, Judee K. Burgoon, William F. Felix

Research output: Contribution to journal › Article › peer-review

247 Scopus citations

Abstract

The strategic use of deceptive language in managerial financial fraud is investigated with linguistic cues extracted from 202 publicly available financial disclosures. Those crafting fraudulent disclosures use more activation language, words, imagery, pleasantness, group references, and less lexical diversity than non-fraudulent ones. Writers of fraudulent disclosures may write more to appear credible while communicating less in actual content. A parsimonious model with Naïve Bayes and C4.5 achieved the highest classification accuracy. Results support the potential use of linguistic analyses by auditors to flag questionable financial disclosures and to assess fraud risk under Statement on Auditing Standards No. 99.

Original language	English (US)
Pages (from-to)	585-594
Number of pages	10
Journal	Decision Support Systems
Volume	50
Issue number	3
DOIs	https://doi.org/10.1016/j.dss.2010.08.009
State	Published - Feb 2011

Keywords

Classification
Deception
Financial fraud
Fraud risk
SAS 99
Text mining

ASJC Scopus subject areas

Management Information Systems
Information Systems
Developmental and Educational Psychology
Arts and Humanities (miscellaneous)
Information Systems and Management

Access to Document

10.1016/j.dss.2010.08.009

Cite this

@article{d8abdc9707ac45fca73ee71f7fcfaec0,

title = "Identification of fraudulent financial statements using linguistic credibility analysis",

abstract = "The strategic use of deceptive language in managerial financial fraud is investigated with linguistic cues extracted from 202 publicly available financial disclosures. Those crafting fraudulent disclosures use more activation language, words, imagery, pleasantness, group references, and less lexical diversity than non-fraudulent ones. Writers of fraudulent disclosures may write more to appear credible while communicating less in actual content. A parsimonious model with Na{\"i}ve Bayes and C4.5 achieved the highest classification accuracy. Results support the potential use of linguistic analyses by auditors to flag questionable financial disclosures and to assess fraud risk under Statement on Auditing Standards No. 99.",

keywords = "Classification, Deception, Financial fraud, Fraud risk, SAS 99, Text mining",

author = "Humpherys, {Sean L.} and Moffitt, {Kevin C.} and Burns, {Mary B.} and Burgoon, {Judee K.} and Felix, {William F.}",

note = "Funding Information: Sean Humpherys is a Ph.D. Candidate with the Center for the Management of Information Systems at Eller College of Management at the University of Arizona. His primary research interests include: Computer-assisted deception detection, HCI, machine-learning algorithms, data mining, and computational linguistics. He researches on projects funded by Department of Defense, Department of Homeland Security, National Science Foundation, Center for Identification Technology Research, National Center for Border Security and Immigration, and PwC. Funding Information: We are pleased to acknowledge the generous support from PricewaterhouseCoopers' INQuiries Research Grant . ",

year = "2011",

month = feb,

doi = "10.1016/j.dss.2010.08.009",

language = "English (US)",

volume = "50",

pages = "585--594",

journal = "Decision Support Systems",

issn = "0167-9236",

publisher = "Elsevier B.V.",

number = "3",

}

TY - JOUR

T1 - Identification of fraudulent financial statements using linguistic credibility analysis

AU - Humpherys, Sean L.

AU - Moffitt, Kevin C.

AU - Burns, Mary B.

AU - Burgoon, Judee K.

AU - Felix, William F.

N1 - Funding Information: Sean Humpherys is a Ph.D. Candidate with the Center for the Management of Information Systems at Eller College of Management at the University of Arizona. His primary research interests include: Computer-assisted deception detection, HCI, machine-learning algorithms, data mining, and computational linguistics. He researches on projects funded by Department of Defense, Department of Homeland Security, National Science Foundation, Center for Identification Technology Research, National Center for Border Security and Immigration, and PwC. Funding Information: We are pleased to acknowledge the generous support from PricewaterhouseCoopers' INQuiries Research Grant .

PY - 2011/2

Y1 - 2011/2

N2 - The strategic use of deceptive language in managerial financial fraud is investigated with linguistic cues extracted from 202 publicly available financial disclosures. Those crafting fraudulent disclosures use more activation language, words, imagery, pleasantness, group references, and less lexical diversity than non-fraudulent ones. Writers of fraudulent disclosures may write more to appear credible while communicating less in actual content. A parsimonious model with Naïve Bayes and C4.5 achieved the highest classification accuracy. Results support the potential use of linguistic analyses by auditors to flag questionable financial disclosures and to assess fraud risk under Statement on Auditing Standards No. 99.

AB - The strategic use of deceptive language in managerial financial fraud is investigated with linguistic cues extracted from 202 publicly available financial disclosures. Those crafting fraudulent disclosures use more activation language, words, imagery, pleasantness, group references, and less lexical diversity than non-fraudulent ones. Writers of fraudulent disclosures may write more to appear credible while communicating less in actual content. A parsimonious model with Naïve Bayes and C4.5 achieved the highest classification accuracy. Results support the potential use of linguistic analyses by auditors to flag questionable financial disclosures and to assess fraud risk under Statement on Auditing Standards No. 99.

KW - Classification

KW - Deception

KW - Financial fraud

KW - Fraud risk

KW - SAS 99

KW - Text mining

UR - http://www.scopus.com/inward/record.url?scp=78651081431&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78651081431&partnerID=8YFLogxK

U2 - 10.1016/j.dss.2010.08.009

DO - 10.1016/j.dss.2010.08.009

M3 - Article

AN - SCOPUS:78651081431

SN - 0167-9236

VL - 50

SP - 585

EP - 594

JO - Decision Support Systems

JF - Decision Support Systems

IS - 3

ER -

Identification of fraudulent financial statements using linguistic credibility analysis

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this