We investigate a novel dataset of more than half a million 15 second transcribed audio snippets containing COVID-19 mentions from major US TV stations throughout 2020. Using the Latent Dirichlet Allocation, an unsupervised machine learning algorithm, we identify seven COVID-19 related topics...

In this study, we examine whether and how tone management affects future stock price crash risk, measured as the conditional skewness of firm-specific returns. We document a positive relationship between tone management and one-year-ahead crash risk. The relationship is more pronounced for firms...

In this study, we examine the predictability of firm-specific stock price crashes using modern machine learning techniques and develop a crash prediction model that utilizes both financial ratios and textual data from the Management Discussion and Analysis (MD&A) of 10-K files. We show that...