Paper Type

Complete

Abstract

Biodiversity continues to decrease, with coal mining companies significantly impacting this trend. This research investigates how transparently these companies address biodiversity issues in their sustainability (or ESG) reports. We develop an assessment framework and apply it to analyze the content of these reports using large language models (LLMs), such as GPT-4, and validate results with human experts’ analyses. This research contributes to expanding the literature on biodiversity reporting and highlights how LLMs can leverage qualitative research using content analysis. Our findings show that while coal mining companies report biodiversity conservation policies, strategies, targets, and plans, their sustainability reports lack detailed impact reporting, comprehensive data, and the use of systematic approaches to effectively mitigate biodiversity loss. This research also illustrates that LLMs have the potential to digest and analyze lengthy sustainability reports more efficiently by automating comprehension and text generation.

Paper Number

1292

Author Connect URL

https://authorconnect.aisnet.org/conferences/AMCIS2025/papers/1292

Comments

SIGGREEN

Author Connect Link

Share

COinS
 
Aug 15th, 12:00 AM

Assessing Biodiversity Reporting in the Coal Mining Industry: Leveraging Large Language Models

Biodiversity continues to decrease, with coal mining companies significantly impacting this trend. This research investigates how transparently these companies address biodiversity issues in their sustainability (or ESG) reports. We develop an assessment framework and apply it to analyze the content of these reports using large language models (LLMs), such as GPT-4, and validate results with human experts’ analyses. This research contributes to expanding the literature on biodiversity reporting and highlights how LLMs can leverage qualitative research using content analysis. Our findings show that while coal mining companies report biodiversity conservation policies, strategies, targets, and plans, their sustainability reports lack detailed impact reporting, comprehensive data, and the use of systematic approaches to effectively mitigate biodiversity loss. This research also illustrates that LLMs have the potential to digest and analyze lengthy sustainability reports more efficiently by automating comprehension and text generation.

When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.