GGOSinonD/Text-Mining-Amazon-Reviews-Polarity

🛍️ Amazon Reviews Sentiment Polarity App

This is a Streamlit app that performs sentiment analysis on Amazon product reviews using a fine-tuned BERT model.

🔗 Live Demo: View on Hugging Face Spaces

🚀 Features

• —🔎 Global Sentiment Analysis — Predicts the overall sentiment of the entire review.
• —✂️ Sentence-Level Predictions — Splits the review into sentences and classifies each individually.
• —🎨 Color-Coded Output:
• —✅ Positive → green highlight
• —❌ Negative → red highlight
• —⚪ Neutral (score < 0.6) → no highlight
• —🖱️ Hover Animation — Hover over any sentence to see the sentiment confidence score.

📚 Model Used

• —AdamCodd/distilbert-base-uncased-finetuned-sentiment-amazon
• —Hosted on Hugging Face 🤗
• —Fine-tuned for sentiment analysis on Amazon reviews

🧪 Example Review

"The build quality is decent. I absolutely love the screen! The battery is okay. But the software is very buggy."

• —Global Prediction: Negative
• —Shows sentence-by-sentence classification with hover scores and color highlights.

🧰 How to Run Locally

git clone https://huggingface.co/spaces/GGOSinonD/Text-Mining-Amazon-Reviews-Polarity
cd Text-Mining-Amazon-Reviews-Polarity
pip install -r requirements.txt
streamlit run app.py