We’re using cookies, but you can turn them off in Privacy Settings.  Otherwise, you are agreeing to our use of cookies.  Accepting cookies does not mean that we are collecting personal data. Learn more in our Privacy Policy.

view of bridge

Can a deep-learning model tell us whether US public firms take their own ESG pronouncements to heart?


Authors: Sudheer Chava, Wendi Du, Baridhi Malakar

Download PDF

Abstract

The authors train a deep-learning based Natural Language Processing (NLP) model on various corporate sustainability frameworks in order to construct a comprehensive Environmental and Social (E&S) dictionary that incorporates materiality. They analyze the earnings conference calls of U.S. public firms during 2007-2019 using this dictionary.

The authors find that the discussion of environmental topics is associated with higher pollution abatement and more future green patents. Firms reduced their air pollution even after the U.S. announced its withdrawal from the Paris Agreement. Similarly, the discussion of social topics is positively associated with improved employee ratings. Overall, the results provide some evidence that firms do walk their talk on E&S issues.

This paper was submitted for the Asia Pacific Research Exchange Award at the 2021 New Zealand Finance Meeting.

Publisher

ARX Editorial Team

Senior Director: Scott Lee
Project Manager: Natalie Yiu
Coordinator: Christy Leung

Share on Facebook Share on Weibo Share on Twitter Share on LinkedIn