Finbert Sentiment Ko

🚀 FinBERT Sentiment Analysis (Korean, Finance Domain)

This model is a BERT-based model fine-tuned for sentiment classification of Korean exchange rate (finance) news summaries. Sentiment classification is performed into one of the following three classes:

• 0: Negative
• 1: Neutral
• 2: Positive

🚀 Quick Start

from transformers import pipeline

pipe = pipeline("text-classification", model="DataWizardd/finbert-sentiment-ko")

pipe("환율이 급등하며 시장 불안이 커지고 있다.")
# Output: [{'label': '부정', 'score': 0.95}]

✨ Features

This model is specifically fine-tuned for sentiment classification of Korean exchange rate (finance) news summaries, providing high accuracy in the finance domain.

📦 Installation

No specific installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

from transformers import pipeline

pipe = pipeline("text-classification", model="DataWizardd/finbert-sentiment-ko")

pipe("환율이 급등하며 시장 불안이 커지고 있다.")
# Output: [{'label': '부정', 'score': 0.95}]

📚 Documentation

🧠 Training Information

• Base Model: snunlp/KR-FinBERT-SC
• Data: Self-collected summaries of Naver exchange rate (finance) news + manual sentiment labeling
• Total number of samples: Approximately 200
• Optimizer: AdamW
• Epochs: 4
• Maximum length: 128
• Evaluation metrics: Accuracy, F1 Score

📊 Performance Evaluation

Overall accuracy: 93% Macro F1-score: 0.92

📄 License

This model is licensed under the MIT license.