language: en
tags:
- financial-text-analysis
- esg
- environmental-social-corporate-governance
widget:
- text: >-
For 2002, our total net emissions were approximately 60 million metric
tons of CO2 equivalents for all businesses and operations we have financial
interests in, based on its equity share in those businesses and
operations.
ESG analysis can help investors determine a business' long-term sustainability and identify associated risks. finbERT-esg-9-categories is a FinBERT model fine-tuned on about 14,000 manually annotated sentences from firms' ESG reports and annual reports.
finbert-esg-9-categories classifies a financial text into 9 fine-grained ESG classes: Climate Change, Natural Capital, Pollution & Waste, Human Capital, Product Liability, Community Relations, Corporate Governance, Business Ethics & Values, and Non-ESG. It complements finbert-esg which classifies a text into 4 coarse-grained ESG categories (E, S, G or None).
Input: A financial text.
Output: Climate Change, Natural Capital, Pollution & Waste, Human Capital, Product Liability, Community Relations, Corporate Governance, Business Ethics & Values, or Non-ESG.
How to use
You can use this model with Transformers pipeline for fine-grained ESG 9 categories classification.
from transformers import BertTokenizer, BertForSequenceClassification, pipeline
finbert = BertForSequenceClassification.from_pretrained('yiyanghkust/finbert-esg-9-categories',num_labels=9)
tokenizer = BertTokenizer.from_pretrained('yiyanghkust/finbert-esg-9-categories')
nlp = pipeline("text-classification", model=finbert, tokenizer=tokenizer)
results = nlp('For 2002, our total net emissions were approximately 60 million metric tons of CO2 equivalents for all businesses
and operations we have financial interests in, based on its equity share in those businesses and operations.')
print(results) # [{'label': 'Climate Change', 'score': 0.9955655932426453}]