Unfolding the Transitions in Sustainability Reporting

• Published in: Sustainability 2024-01, Vol.16 (2), p.809
• Main Authors: Li, Yao, Rockinger, Michael
• Format: Article
• Language: English
• Subjects: Accounting periods; Annual reports; Banking industry; Banks; Classification; Computational linguistics; Financial disclosure; Financial institutions; Financial statements; Green market; Language processing; Natural language interfaces; Neural networks; Sustainability reporting; Sustainable development; Text analysis
• ISSN: 2071-1050; 2071-1050
• DOI: 10.3390/su16020809

The sustainable development goals (SDGs) have been widely embraced by organizations as a sign of their commitment to sustainability. In this study, we develop a novel SDG-related bidirectional encoder representations from transformers (BERT) model, using the neural network methodology, to determine the thematic evolution of European banks’ sustainability reports. We train this model on the OSDG-CD corpus, which we extend by labeling approximately 10,000 sentences based on SDGs content. The classification capabilities of this model appear to be very effective. Analysts who use our methodology can make faster decisions about the sustainability claims of financial institutions. Our methodology can be extended to non-financial entities. By analyzing the sustainability reports of 98 listed banks covering the accounting periods ranging from 2010 to 2022, we can identify the temporal emphasis of the SDGs. By 2022, climate action had emerged as the most important focus theme. We further validate our classification methodology by establishing a strong correlation between the evolution of SDG prevalence and relevant macroeconomic indicators. We also reveal a difference in focus between various European regions. Finally, we use word counts and k-means cluster analysis to document changes in the objectives of banks by investigating their discussion content.