|
--- |
|
language: |
|
- en |
|
thumbnail: https://cdn.pixabay.com/photo/2017/09/07/08/54/money-2724241__340.jpg |
|
tags: |
|
- text-classification |
|
- sentiment-analysis |
|
- finance-sentiment-detection |
|
- finance-sentiment |
|
license: apache-2.0 |
|
datasets: |
|
- cyrilzhang/financial_phrasebank_split |
|
metrics: |
|
- Accuracy, F1 score |
|
widget: |
|
- text: "HK stocks open lower after Fed rate comments" |
|
example_title: "HK stocks open lower" |
|
- text: "US stocks end lower on earnings worries" |
|
example_title: "US stocks end lower" |
|
- text: "Muted Fed, AI hopes send Wall Street higher" |
|
example_title: "Muted Fed" |
|
|
|
--- |
|
## nickwong64/bert-base-uncased-finance-sentiment |
|
Bert is a Transformer Bidirectional Encoder based Architecture trained on MLM(Mask Language Modeling) objective. |
|
[bert-base-uncased](https://huggingface.co/bert-base-uncased) finetuned on the [cyrilzhang/financial_phrasebank_split](https://huggingface.co/datasets/cyrilzhang/financial_phrasebank_split) dataset using HuggingFace Trainer with below training parameters. |
|
``` |
|
learning rate 2e-5, |
|
batch size 8, |
|
num_train_epochs=6, |
|
``` |
|
|
|
## Model Performance |
|
| Epoch | Training Loss | Validation Loss | Accuracy | F1 | |
|
| --- | --- | --- | --- | --- | |
|
| 6 | 0.034100 | 0.954745 | 0.853608 | 0.854358 | |
|
|
|
|
|
|
|
## How to Use the Model |
|
```python |
|
from transformers import pipeline |
|
nlp = pipeline(task='text-classification', |
|
model='nickwong64/bert-base-uncased-finance-sentiment') |
|
p1 = "HK stocks open lower after Fed rate comments" |
|
p2 = "US stocks end lower on earnings worries" |
|
p3 = "Muted Fed, AI hopes send Wall Street higher" |
|
print(nlp(p1)) |
|
print(nlp(p2)) |
|
print(nlp(p3)) |
|
""" |
|
output: |
|
[{'label': 'negative', 'score': 0.9991507530212402}] |
|
[{'label': 'negative', 'score': 0.9997240900993347}] |
|
[{'label': 'neutral', 'score': 0.9834381937980652}] |
|
""" |
|
``` |
|
|
|
## Dataset |
|
[cyrilzhang/financial_phrasebank_split](https://huggingface.co/datasets/cyrilzhang/financial_phrasebank_split) |
|
|
|
## Labels |
|
``` |
|
{0: 'negative', 1: 'neutral', 2: 'positive'} |
|
``` |
|
|
|
## Evaluation |
|
``` |
|
{'test_loss': 0.9547446370124817, |
|
'test_accuracy': 0.8536082474226804, |
|
'test_f1': 0.8543579048224414, |
|
'test_runtime': 4.9865, |
|
'test_samples_per_second': 97.263, |
|
'test_steps_per_second': 12.233} |
|
``` |
|
|