Cheap Talk and Cherry-Picking: What ClimateBert has to say on Corporate Climate Risk Disclosures

Bingler JA, Kraus M, Leippold M (2021)

Publication Type: Journal article, Original article

Publication year: 2021

Journal

Social Science Research Network Elsevier

Original Authors: Julia Anna Bingler, Mathias Kraus, Markus Leippold

DOI: 10.2139/ssrn.3796152

Abstract

Disclosure of climate-related financial risks greatly helps investors assess companies' preparedness for climate change. Voluntary disclosures such as those based on the recommendations of the Task Force for Climate-related Financial Disclosures (TCFD) are being hailed as an effective measure for better climate risk management. We ask whether this expectation is justified. We do so with the help of a deep neural language model, which we christen ClimateBert. We train ClimateBert on thousands of sentences related to climate-risk disclosures aligned with the TCFD recommendations. In analyzing the disclosures of TCFD-supporting firms, ClimateBert comes to the sobering conclusion that the firms' TCFD support is mostly cheap talk and that firms cherry-pick to report primarily non-material climate risk information. From our analysis, we conclude that the only way out of this dilemma is to turn voluntary reporting into regulatory disclosures.

Authors with CRIS profile

Mathias Kraus Juniorprofessur für Data Analytics

Involved external institutions

Eidgenössische Technische Hochschule Zürich (ETHZ) / Swiss Federal Institute of Technology in Zurich CH Switzerland (CH) University of Zurich / Universität Zürich (UZH) CH Switzerland (CH)

How to cite

APA:

Bingler, J.A., Kraus, M., & Leippold, M. (2021). Cheap Talk and Cherry-Picking: What ClimateBert has to say on Corporate Climate Risk Disclosures. Social Science Research Network. https://dx.doi.org/10.2139/ssrn.3796152

MLA:

Bingler, Julia Anna, Mathias Kraus, and Markus Leippold. "Cheap Talk and Cherry-Picking: What ClimateBert has to say on Corporate Climate Risk Disclosures." Social Science Research Network (2021).

BibTeX: Download