Update README.md

README.md

@@ -1,61 +1,22 @@
-# ISOM5240 Project: Amazon Review Sentiment Analysis
+# Amazon Review Sentiment Analysis
 
-## Team Members
-- Jishen Wang
-- Shen Yishan
+This Streamlit application analyzes the sentiment of product reviews and predicts ratings (1-5 stars) using a pre-trained model from Hugging Face.
 
-## Project Structure
-```
-ISOM5240_Project/
-├── README.md               # Project overview and setup instructions
-├── requirements.txt        # Python dependencies
-├── docs/                  # Documentation
-│   ├── project_report.md  # Project report in markdown format
-│   └── project_report.pdf # Project report in PDF format
-├── src/                   # Source code
-│   ├── app.py            # Streamlit web application
-│   ├── model.py          # Sentiment analysis model implementation
-│   ├── preprocessing.py  # Text preprocessing utilities
-│   └── utils.py         # General utility functions
-├── data/                 # Data directory for storing datasets
-└── notebooks/           # Jupyter notebooks for analysis
-```
-
-## Setup Instructions
-1. Clone this repository
-2. Install dependencies:
-```bash
-pip install -r requirements.txt
-```
-
-## Running the Application
-1. Navigate to the project directory:
-```bash
-cd ISOM5240_Project
-```
-
-2. Run the Streamlit application:
-```bash
-streamlit run src/app.py
-```
-
-3. Access the web interface at: http://localhost:8501
-
-## Documentation
-- Detailed project documentation can be found in the `docs` directory
-- The project report is available in both markdown and PDF formats
+## Features
+- Real-time sentiment analysis of product reviews
+- Rating prediction (1-5 stars)
+- Confidence scores for each rating
+- Multi-language support (English, Dutch, German, French, Spanish, Italian)
 
 ## Model Information
-- Using HuggingFace's LiYuan/amazon-review-sentiment-analysis model
-- Multi-language support for sentiment analysis
-- Real-time analysis through web interface
+The application uses the [LiYuan/amazon-review-sentiment-analysis](https://huggingface.co/LiYuan/amazon-review-sentiment-analysis) model from Hugging Face, which is based on DistilBERT and was trained on a large dataset of Amazon product reviews.
 
-## Features
-1. Sentiment analysis of product reviews
-2. Multi-language support
-3. Rating prediction (1-5 stars)
-4. Web interface for real-time analysis
-5. Batch processing capabilities
-6. Results visualization and export options 
+## Usage
+1. Enter your review text in the text area
+2. Click "Analyze Sentiment"
+3. View the predicted rating and confidence scores
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+## Technical Details
+- Built with Streamlit
+- Uses PyTorch and Transformers
+- Model is cached for faster inference