Summary Advances in Deep Learning have drastically improved the abilities of Natural
Language Processing (NLP) research, creating new state‐of‐the‐art benchmarks. Two …

We investigate the effects of a qualitative tax disclosure mandate aimed at improving tax
transparency and compliance by imposing reputational costs for firms. We use, as an …

We investigate (1) how well a machine learning algorithm can predict one-year ahead
effective tax rates (ETRs) and (2) which items in the financial statements and notes are most …

Purpose The purpose of this paper is to explore how variations in management's tone within
management's discussion and analysis (MD&A) sections of 10-K reports can serve as an …

Previous studies have shown that qualitative disclosure contains information that facilitates
the assessment of future firm outcomes. We first connect to this literature on early signals by …

Using a model from political economy, we predict that US Internal Revenue Code sections
and related Treasury Regulations will have more verbiage, complex terms, and cognitive …

We create a measure of “discussed numbers” that captures the narrative context of numbers
reported in financial statements. Our algorithm matches words within XBRL tags to …

As an essential communication medium, the internet brings the freedom and convenience of
publishing, transmitting, and acquiring information. At the same time, the problems caused …

We investigate the effects of a qualitative tax disclosure mandate aimed at improving tax
transparency and compliance by imposing reputational costs for firms. We use, as an …

This study examines the determinants and implications of the volume of tax-related numbers
reported in the financial statements. I document that the volume of tax-related numbers …