#Fail: Social Media, Firm Distress, and Going Concern Opinions

• In Event: Going Concern and Financial Distress

Abstract

Research identifies a number of settings in which the opinions of social media users reflect information useful to capital market participants, including investors and analysts. We extend this research by examining whether social media could be useful for auditors. Specifically, we investigate whether the opinions of users on the social media platform StockTwits provide information relevant to evaluating firms in financial distress. We find that social media sentiment, measured using message bearishness and probability of failure derived from a machine-learning algorithm, relates positively to both the likelihood of firm failure and the likelihood a firm’s auditor issues a going-concern opinion. In other words, negative sentiment is associated with a higher likelihood of failure and a going concern modification. However, we find minimal evidence that the presence of a going-concern opinion mediates the association between social media sentiment and failure, suggesting auditors do not fully incorporate this publicly available information. We also provide evidence that naïve consideration of social media sentiment reduces Type II errors at a faster rate than the corresponding increase in Type I errors. Our evidence should be informative to regulators and audit firms, both of whom are currently evaluating how the proliferation of data on social media can be useful to auditors.

Authors

• Eric Condie, Georgia Institute of Technology

• James Robert Moon, Georgia Institute of Technology