Detecting Deceptive Discussions in Conference Calls

We estimate linguistic‐based classification models of deceptive discussions during quarterly earnings conference calls. Using data on subsequent financial restatements and a set of criteria to identify severity of accounting problems, we label each call as “truthful” or “deceptive.” Prediction models are then developed with the word categories that have been shown by previous psychological and linguistic research to be related to deception. We find that the out‐of‐sample performance of models based on CEO and/or CFO narratives is significantly better than a random guess by 6–16% and is at least equivalent to models based on financial and accounting variables. The language of deceptive executives exhibits more references to general knowledge, fewer nonextreme positive emotions, and fewer references to shareholder value. In addition, deceptive CEOs use significantly more extreme positive emotion and fewer anxiety words. Finally, a portfolio formed from firms with the highest deception scores from CFO narratives produces an annualized alpha of between −4% and −11%.

[1]  T. Yohn,et al.  Restatements: Investor Response and Firm Reporting Choices , 2008 .

[2]  Mike Y. Chen,et al.  Yahoo! for Amazon: Sentiment Extraction from Small Talk on the Web , 2001 .

[3]  D. Larcker,et al.  The Power of the Pen and Executive Compensation , 2007 .

[4]  J. Courtis,et al.  Corporate report obfuscation: artefact or phenomenon? , 2004, The British Accounting Review.

[5]  Adrienne Y. Lee,et al.  Language of lies in prison: linguistic classification of prisoners' truthful and deceptive natural language , 2005 .

[6]  Sofus A. Macskassy,et al.  More than Words: Quantifying Language to Measure Firms' Fundamentals the Authors Are Grateful for Assiduous Research Assistance from Jie Cao and Shuming Liu. We Appreciate Helpful Comments From , 2007 .

[7]  A. Leone,et al.  Measuring Qualitative Information in Capital Markets Research , 2009 .

[8]  Vernon J. Richardson,et al.  Determinants of Market Reactions to Restatement Announcements , 2001 .

[9]  James J. Lindsay,et al.  Cues to deception. , 2003, Psychological bulletin.

[10]  D. BeneishMessod,et al.  The Detection of Earnings Manipulation , 1999 .

[11]  Paul C. Tetlock.  Giving Content to Investor Sentiment: The Role of Media in the Stock Market , 2005, The Journal of Finance.

[12]  Werner Antweiler,et al.  Is All that Talk Just Noise? The Information Content of Internet Stock Message Boards , 2001 .

[13]  Patricia M. Dechow,et al.  Predicting Material Accounting Misstatements*: Predicting Material Accounting Misstatements , 2011 .

[14]  Jeremy Piger,et al.  Louis Working Paper Series Beyond the Numbers : An Analysis of Optimistic and Pessimistic Language in Earnings Press Releases , 2006 .

[15]  S. Kothari,et al.  The Effect of Disclosures by Management, Analysts, and Business Press on Cost of Capital, Return Volatility, and Analyst Forecasts: A Study Using Content Analysis , 2009 .

[16]  Kevin C. Moffitt,et al.  Identification of fraudulent financial statements using linguistic credibility analysis , 2011, Decis. Support Syst..

[17]  D. Collins,et al.  Errors in Estimating Accruals: Implications for Empirical Research , 1999 .

[18]  J. Pennebaker,et al.  Lying Words: Predicting Deception from Linguistic Styles , 2003, Personality & social psychology bulletin.

[19]  Feng Li.  Do Stock Market Investors Understand the Risk Sentiment of Corporate Annual Reports? , 2006 .

[20]  Susan H. Adams,et al.  Indicators of veracity and deception: an analysis of written statements made to police , 2006 .

[21]  Andrew J. Leone,et al.  The Importance of Distinguishing Errors from Irregularities in Restatement Research: The Case of Restatements and CEO/CFO Turnover , 2008 .

[22]  Alan D. Jagolinzer,et al.  Chief Executive Officer Equity Incentives and Accounting Irregularities , 2009 .

[23]  Yoshua Bengio,et al.  Inference for the Generalization Error , 1999, Machine Learning.

[24]  William J. Mayew,et al.  Analyzing Speech to Detect Financial Misreporting , 2011 .

[25]  Ian D. Gow,et al.  Rating the Ratings: How Good are Commercial Governance Ratings? , 2010 .

[26]  S. B. Thompson.  Simple Formulas for Standard Errors that Cluster by Both Firm and Time , 2009 .

[27]  Patricia M. Dechow,et al.  The Quality of Accruals and Earnings: The Role of Accrual Estimation Errors , 2002 .

[28]  Feng Li.  Annual Report Readability, Current Earnings, and Earnings Persistence , 2008 .

[29]  J. Jones.  Earnings Management During Import Relief Investigations , 1991 .

[30]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[31]  Kurt Hornik,et al.  Text Mining Infrastructure in R , 2008 .

[32]  Padmini Srinivasan,et al.  On the predictive ability of narrative disclosures in annual reports , 2010, Eur. J. Oper. Res..

[33]  Thomas G. Dietterich.  Approximate Statistical Tests for Comparing Supervised Classification Learning Algorithms , 1998, Neural Computation.

[34]  Richard A. Price,et al.  Detecting and Predicting Accounting Irregularities: A Comparison of Commercial and Academic Risk Measures , 2011 .

[35]  Charles E. Wasley,et al.  Performance Matched Discretionary Accrual Measures , 2002 .

[36]  Gopal V. Krishnan,et al.  Do Models of Discretionary Accruals Detect Actual Cases of Fraudulent and Restated Earnings? An Empirical Evaluation , 2008 .

[37]  Trevor Hastie,et al.  Regularization Paths for Generalized Linear Models via Coordinate Descent. , 2010, Journal of statistical software.

[38]  M. Knapp,et al.  An Exploration of Deception as a Communication Construct , 1974 .

[39]  Thomas Lengauer,et al.  ROCR: visualizing classifier performance in R , 2005, Bioinform..

[40]  Richard G. Sloan,et al.  Accrual Reliability, Earnings Persistence and Stock Prices , 2005 .

[41]  E. Fama,et al.  Common risk factors in the returns on stocks and bonds , 1993 .

[42]  Eileen Fitzpatrick,et al.  Verification and Implementation of Language-Based Deception Indicators in Civil and Criminal Narratives , 2008, COLING.

[43]  Clara Vega,et al.  Soft information in earnings announcements: news or noise? , 2008 .

[44]  Mark M. Carhart.  On Persistence in Mutual Fund Performance , 1997 .

[45]  Feng Li.  The Information Content of Forward-Looking Statements in Corporate Filings—A Naïve Bayesian Machine Learning Approach , 2010 .

[46]  Tim Loughran,et al.  When is a Liability not a Liability? Textual Analysis, Dictionaries, and 10-Ks , 2010 .

[47]  M. McNichols.  Research design issues in earnings management studies , 2000 .

[48]  Bill McDonald,et al.  A Wolf in Sheep’s Clothing: The Use of Ethics-Related Terms in 10-K Reports , 2007 .

[49]  Ian D. Gow,et al.  Correcting for Cross-Sectional and Time-Series Dependence in Accounting Research , 2009 .