Treffer: Unveiling two decades of environmental policy research trends: topic modeling-based machine learning insights.

Purpose: The study aims to analyze and report on key research trends within the environmental policy (EPOL) discipline, focusing on identifying important topic areas and highlighting the theoretical concepts and analysis methods that policy scholars should prioritize. By exploring these aspects, the study seeks to enhance policy effectiveness in addressing environmental challenges. Design/methodology/approach: The study uses a content analytics approach, employing the Latent Dirichlet Allocation (LDA) model to identify research hotspots. The LDA model analyzes research trends across 2 decades (2000–2019), based on a dataset of 33,683 abstracts from 30 peer-reviewed journals focused on EPOL research. This methodology enables a comprehensive examination of emerging topics within the discipline. Findings: The analysis identifies 40 significant research topics within the EPOL literature. Key findings highlight the increasing focus on niche areas such as climate change resilience, food security, renewable energy, urban spatial planning and ecosystem services. These trends reflect a shift towards more specialized and targeted policy issues within the broader field of EPOL. Originality/value: This study provides a novel contribution to EPOL scholarship by offering a quantitative, data-driven analysis of research trends over the past 2 decades. The use of the LDA model for profiling research hotspots introduces a new perspective on how to systematically track and synthesize emerging EPOL topics. The findings have the potential to inform future research and policy development by fostering a more integrative understanding of the field. [ABSTRACT FROM AUTHOR]

Copyright of Management of Environmental Quality: An International Journal is the property of Emerald Publishing Limited and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)