Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/320452 
Year of Publication: 
2025
Citation: 
[Journal:] Junior Management Science (JUMS) [ISSN:] 2942-1861 [Volume:] 10 [Issue:] 2 [Year:] 2025 [Pages:] 369-401
Publisher: 
Junior Management Science e. V., Planegg
Abstract: 
Sustainability has become a crucial factor in the financial sector, making the assessment of a company's sustainability performance essential for informed decision-making. Recognizing the media's power to shape public perception of corporate sustainability issues, this study examines the use of news analysis to evaluate companies' performance against Environmental, Social, and Governance (ESG) criteria. Leveraging OpenAI's models, this research parses unstructured data within news articles and introduces a machine learning pipeline to score companies' ESG performance based on their media representation. The study uncovers several key findings: firstly, it demonstrates that a less costly, fine-tuned model can surpass the zero-shot capabilities of a more expensive model in classifying ESG content. Secondly, it identifies discrepancies in media coverage across industries, leading to unequal assessments of companies. Thirdly, it reveals a media tendency to underreport companies' environmental efforts. Finally, the study highlights areas where companies face media criticism, suggesting potential improvements in their ESG practices. These insights contribute to the understanding of how machine learning can assist in the critical evaluation of sustainability in the business domain.
Subjects: 
ESG
machine learning
natural language processing
news
NLP
sustainability
Persistent Identifier of the first edition: 
Creative Commons License: 
cc-by Logo
Document Type: 
Article
Appears in Collections:

Files in This Item:
File
Size





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.