YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Japanese Sentiment Analysis v1

Model Description
Fine-tuned Japanese BERT model for 3-class sentiment analysis (Positive / Neutral / Negative) on e-commerce reviews and customer feedback.

  • Base model: cl-tohoku/bert-base-japanese-v2
  • Task: Text Classification
  • Language: Japanese
  • License: MIT
  • Developer: Retro099 (portfolio project)

How to Use

from transformers import pipeline

classifier = pipeline("sentiment-analysis", 
                      model="Retro099/japanese-sentiment-analysis-v1",
                      device=-1)   # CPU for local / Streamlit Cloud

result = classifier("この商品は最高です!とても満足しています。")
print(result)

Label Mapping

LABEL_0 → Negative 😞
LABEL_1 → Neutral 😐
LABEL_2 → Positive 😊

日本語要約
日本語のレビューやテキストに対する感情分析モデルを構築しました。Hugging Face Transformers + PyTorchを使用してBERTをファインチューニングし、Positive/Negative/Neutralの3クラス分類を実現。eコマースにおける顧客満足度分析や自動レビュー分類に活用可能です。GradioデモとStreamlit Cloudデプロイ済みです。
Live Demos

Streamlit Cloud: https://cx7v54ehccpwnarlaplxt.streamlit.app/
Gradio (temporary): https://f50c787d7b105f7bf9.gradio.live/
GitHub Repo: https://github.com/Retro099/ML-Projects/tree/main/Japanese_Sentiment_Analysis
Downloads last month
73
Safetensors
Model size
0.1B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support