Detecting Deceptive Discussions in Conference Calls



    1. Graduate School of Business, Rock Center for Corporate Governance, Stanford University
    Search for more papers by this author

    1. Graduate School of Business, Stanford University. We would like to thank Thomas Quinn for his help in securing the FactSet data, and John Johnson and Ravi Pillai for their help with computational issues. The comments of Maria Correia, Jerome Friedman, Michelle Gutman, Daniel Jurafsky, Sally Larcker, Andrew Leone, Sergey Lobanov, Miguel Angel Minutti Meza, Maria Ogneva, Brian Tayan and participants at the Transatlantic Doctoral Conference 2010 at the London Business School, American Accounting Association Meeting 2010, and 2011 Journal of Accounting Research Conference for helpful discussions. We thank Philip Berger (the Editor), the anonymous referee, and Robert Bloomfield for their excellent suggestions. Larcker also thanks the Joseph and Laurie Lacob Faculty Fellowship for financial support.
    Search for more papers by this author


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%.