yiyanghkust
commited on
Commit
•
013dac0
1
Parent(s):
2cde036
Update README.md
Browse files
README.md
CHANGED
@@ -6,4 +6,22 @@ tags:
|
|
6 |
- environmental-social-corporate-governance
|
7 |
widget:
|
8 |
- text: "Rhonda has been volunteering for several years for a variety of charitable community programs. "
|
9 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
- environmental-social-corporate-governance
|
7 |
widget:
|
8 |
- text: "Rhonda has been volunteering for several years for a variety of charitable community programs. "
|
9 |
+
---
|
10 |
+
|
11 |
+
ESG analysis can help investors determine a business' long-term sustainability and identify associated risks. FinBERT-ESG is a FinBERT model fine-tuned on 2,000 manually annotated sentences from firms' ESG reports and annual reports.
|
12 |
+
|
13 |
+
# How to use
|
14 |
+
You can use this model with Transformers pipeline for sentiment analysis.
|
15 |
+
```python
|
16 |
+
# tested in transformers==4.18.0
|
17 |
+
from transformers import BertTokenizer, BertForSequenceClassification, pipeline
|
18 |
+
|
19 |
+
finbert = BertForSequenceClassification.from_pretrained('yiyanghkust/finbert-esg',num_labels=4)
|
20 |
+
tokenizer = BertTokenizer.from_pretrained('yiyanghkust/finbert-esg')
|
21 |
+
nlp = pipeline("text-classification", model=finbert, tokenizer=tokenizer)
|
22 |
+
results = nlp('Rhonda has been volunteering for several years for a variety of charitable community programs.')
|
23 |
+
print(results) # [{'label': 'Social', 'score': 0.9906041026115417}]
|
24 |
+
|
25 |
+
```
|
26 |
+
|
27 |
+
Visit [FinBERT.AI](https://finbert.ai/) for more details on the recent development of FinBERT.
|