Identifying Key Issues in Climate Change Litigation: A Machine Learning Text Analytic Approach

Abstract

As climate change, environmental, social, and governance (ESG), along with sustainability, become increasingly crucial for businesses and society, there is a noticeable scarcity of information and transparency regarding corporate practices. Often, government agency enforcement actions lead to litigation and are ultimately resolved by court decisions. Moreover, in instances when there is perceived inadequacy in government enforcement, citizens frequently turn to the courts for preventive judgments against businesses or agencies. In an effort to shed light on the multifaceted aspects of climate change, we adopted a novel, exploratory approach to analyze climate change-related litigation cases. Utilizing a blend of machine learning-based text analytics, we have extracted key insights from individual case narratives. Our analysis encompassed over four hundred cases from the Westlaw database through various keyword searches. The emergent topics from our case dataset revolved around four critical environmental themes: forest, land, water, and air emissions. Our findings provide insight into the nature and dimensions of climate change and also carry significant policy implications, laying the groundwork for future research in this domain.