Document Type
Article
Abstract
The global textile and apparel (T&A) industry faces critical pressure over its environmental impact, producing approximately 92 million tons of waste annually and contributing to nearly 20% of global water pollution. For Bangladesh, one of the leading apparel exporters, the integration of transparent Environmental, Social, and Governance (ESG) practices is crucial for meeting international sustainability standards and maintaining global competitiveness. This study proposes a machine learning-based method to analyze ESG practices among LEED-certified T&A factories in Bangladesh. Leveraging contextual Natural Language Processing (NLP) and Topic Modeling technique, we developed a robust Machine learning (ML) framework based on Non-Negative Matrix Factorization (NMF) for topic extraction and a Random Forest classifier for ESG category prediction. We achieve an accuracy of 87% and an F1-score of 0.87 in ESG category prediction on a validated expert-defined keyword set, surpassing the traditional ESG analysis approach. Our analysis identified four key dominant ESG themes: Environmental Sustainability, Social I: Workplace Safety and Compliance, Social II: Education and Community Programs, and Governance. The results also show that 46% of the factories prioritize environmental initiatives such as energy conservation and waste management, 44% focus on social aspects, including safety and education at work, while governance practices are still significantly underrepresented, only in 10%. Overall, our framework offers a scalable, data-driven approach for analyzing corporate sustainability disclosures, providing actionable insights for industry stakeholders, policymakers, and global brands pursuing responsible sourcing in Bangladesh’s T&A sector.
Digital Object Identifier (DOI)
Publication Info
Postprint version. Published in Scientific Reports, 2026.
Rights
© The Author(s) 2026. Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
APA Citation
Magotra, A., Rana, Md. R. I., Shishir, F. S., & Shomaji, S. (2026). A machine learning and NLP pipeline for analyzing ESG and sustainability disclosures in the textile and apparel industry. Scientific Reports.https://doi.org/10.1038/s41598-026-49931-z