|
--- |
|
|
|
|
|
{} |
|
--- |
|
|
|
# Model Card for Model ID |
|
|
|
<!-- Provide a quick summary of what the model is/does. --> |
|
2024.4.4 Update |
|
|
|
This model is a sentiment analysis model designed to determine the positive/neutral/negative sentiment of sentences included in corporate-related news. |
|
|
|
This model is targeted to provide sentiment for "important news", as described in the paper mentioned following. So, the results may not be accurate for less important news. |
|
|
|
It can be used as a Korean-based sentiment analysis model for the finance/management/accounting fields. |
|
|
|
Example> |
|
|
|
"Samsung's debt is increasing." --> Neutral. The mere increase in debt is not necessarily negative. |
|
|
|
"Due to the failure of management strategy, Samsung's debt is increasing." --> Negative. Debt increase due to failure is considered negative. |
|
|
|
Hyun Ji-won, Lee Jun-il, and Cho Hyun-kwon. "A Study on Sentiment Classification of Corporate-related News Articles Using KoBERT." Accounting Research 47.4 (2022): 33-54. |
|
|
|
We have further developed the model proposed in the above paper and made it available through Huggingface. If you use it for research purposes, please cite the above paper. |
|
|
|
This model was fine-tuned using https://huggingface.co/jhgan/ko-sroberta-multitask. |
|
|
|
For the usage code, refer to the link below: |
|
|
|
Google Colab: https://colab.research.google.com/drive/1ORzKUr94cPyc5jaRCAngbclm4Qb4DtdG |
|
|
|
The current evaluation results of the model are as follows: |
|
|
|
{'eval_loss': 0.7330707907676697, 'eval_f1': 0.8689251403360293, 'eval_runtime': 0.464, 'eval_samples_per_second': 2047.32, 'eval_steps_per_second': 17.241, 'epoch': 33.33} |
|
|
|
While the accuracy has increased compared to the paper's 85.7%, the improvement is not significant. |
|
|
|
2024.4.4 Update |
|
|
|
์ด ๋ชจํ์ ๊ธฐ์
๊ด๋ จ ๋ด์ค์ ํฌํจ๋ ๋ฌธ์ฅ์ ๊ธ์ /์ค๋ฆฝ/๋ถ์ ์ ํ๋จํ๊ธฐ ์ํ ๊ฐ์ฑ๋ถ์ ๋ชจํ์
๋๋ค. |
|
|
|
์ด ๋ชจํ์ ํ๋จ ๋
ผ๋ฌธ์์ ์ค๋ช
ํ ๋ฐ์ ๊ฐ์ด ์ค์ํ ๋ด์ค์ ๊ฐ์ฑ๋ถ์๊ฒฐ๊ณผ๋ฅผ ์ ๊ณตํ๋๋ก ํ๋ จ๋์์ผ๋ฏ๋ก, ์ค์์ฑ์ด ๋ฎ์ ๋ด์ค์ ๋ํ ๊ฐ์ฑ๋ถ์ ๊ฒฐ๊ณผ๋ ์ ํํ์ง ์์ ์ ์์ต๋๋ค. |
|
|
|
ํ๊ตญ์ด ๊ธฐ๋ฐ ๊ธ์ต/๊ฒฝ์/ํ๊ณ ๋ถ์ผ ๊ฐ์ฑ๋ถ์ ๋ชจํ์ผ๋ก ์ฌ์ฉํ์๋ฉด ๋ฉ๋๋ค. |
|
|
|
์์> |
|
|
|
์ผ์ฑ์ ์์ ๋ถ์ฑ๊ฐ ์ฆ๊ฐํ๊ณ ์์ต๋๋ค. --> ์ค๋ฆฝ (neutral). ๋ถ์ฑ์ฆ๊ฐ ์์ฒด๋ ๋ถ์ ์ ์ด๋ผ๊ณ ๋ณด๊ธฐ ์ด๋ ค์ |
|
|
|
๊ฒฝ์์ ๋ต์ ์คํจ๋ก ์ผ์ฑ์ ์์ ๋ถ์ฑ๊ฐ ์ฆ๊ฐํ๊ณ ์์ต๋๋ค. --> ๋ถ์ (negative). ์คํจ๋ก ์ธํ ๋ถ์ฑ ์ฆ๊ฐ๋ ๋ถ์ ์ |
|
|
|
ํ์ง์, ์ด์ค์ผ, and ์กฐํ๊ถ. "KoBERT ๋ฅผ ์ด์ฉํ ๊ธฐ์
๊ด๋ จ ์ ๋ฌธ๊ธฐ์ฌ ๊ฐ์ฑ ๋ถ๋ฅ ์ฐ๊ตฌ." ํ๊ณํ์ฐ๊ตฌ 47.4 (2022): 33-54. |
|
|
|
์ ๋
ผ๋ฌธ์์ ์ ์ํ ๋ชจ๋ธ์ ๋ฐ์ ์์ผ huggingface๋ฅผ ํตํด ๊ณต๊ฐํฉ๋๋ค. |
|
์ฐ๊ตฌ์ ์ฌ์ฉํ์ค ๊ฒฝ์ฐ ์ ํ์ดํผ๋ฅผ cite ํด ์ฃผ์๊ธฐ ๋ฐ๋๋๋ค. |
|
|
|
ํด๋น ๋ชจ๋ธ์ https://huggingface.co/jhgan/ko-sroberta-multitask ๋ฅผ ์ฌ์ฉํ์ฌ finetuing ํ ๋ชจํ์
๋๋ค. |
|
|
|
์ฌ์ฉ ์ฝ๋๋ ์๋ ๋งํฌ๋ฅผ ์ฐธ๊ณ ํ์
์ |
|
|
|
๊ตฌ๊ธ ์ฝ๋ฉ: |
|
https://colab.research.google.com/drive/1ORzKUr94cPyc5jaRCAngbclm4Qb4DtdG |
|
|
|
|
|
|
|
|
|
ํ์ฌ ๋ชจํ์ evaluation ๊ฒฐ๊ณผ๋ ๋ค์๊ณผ ๊ฐ์ต๋๋ค. |
|
|
|
{'eval_loss': 0.7330707907676697, |
|
'eval_f1': 0.8689251403360293, |
|
'eval_runtime': 0.464, |
|
'eval_samples_per_second': 2047.32, |
|
'eval_steps_per_second': 17.241, |
|
'epoch': 33.33} |
|
|
|
์ ํ๋ ๊ธฐ์ค์ผ๋ก ๋
ผ๋ฌธ์ 85.7% ์ ๋นํด ์์นํ์์ผ๋, ์์นํญ์ด ํ์ ํ์ง๋ ์์ต๋๋ค. |
|
|
|
## Model Details |
|
|
|
### Model Description |
|
|
|
<!-- Provide a longer summary of what this model is. --> |