Dive into the emotional undercurrents of customer feedback with "SentimentScope for Amazon Reviews". Utilizing the prowess of Natural Language Processing (NLP), this project discerns the sentiments within Amazon product reviews, classifying them with a keen eye into positive, negative, or neutral emotions.
- Refined Sentiment Analysis: Deftly sorts sentiments in Amazon product reviews.
- Advanced NLP with spaCy: Harnesses the cutting-edge processing power of
spaCy
. - Polarity Insight with TextBlob: Leverages
TextBlob
for nuanced sentiment polarity determination. - Robust Dataset Management: Tailored to adeptly navigate and process large datasets.
Begin exploring sentiments in just a few steps:
- Clone the project repository.
- Navigate to the project directory.
- Install dependencies.
- Run the analysis script.
git clone https://github.com/AdrianGeorgeM/SentimentScope-for-Amazon-Reviewss.git
cd SentimentScope-for-Amazon-Reviews
pip install -r requirements.txt
python sentiment_analysis.py
## Data π
The engine analyzes `amazon_product_reviews.csv`, meticulously sifting through the `reviews.text` column. Due to its voluminous nature, the dataset is excluded from this repository.
## Output and Results π
The `sentiment_analysis_output.csv` file encapsulates the essence of customer sentiments, pairing each review with its corresponding sentiment score. Explore sample screenshots in the repository for a vivid snapshot of the analysis.
## Screenshots πΈ
Check out the screenshots in the repository, showcasing sample outputs and the sentiment determination in action.
### Sample Screenshot Descriptions
- **Positive Sentiment**: Reviews expressing satisfaction and highlighting positive aspects.
- **Neutral Sentiment**: Reviews that are objective, neither positive nor negative.
- **Negative Sentiment**: Reviews indicating dissatisfaction or issues with the product.
For an in-depth look, refer to the screenshots in the `/screenshots` directory.
## Contribution π€
Join the crusade to refine sentiment analysis:
- Fork the project.
- Create your feature branch (`git checkout -b feature/AmazingFeature`).
- Commit your changes (`git commit -m 'Add some AmazingFeature'`).
- Push to the branch (`git push origin feature/AmazingFeature`).
- Open a pull request.
## License π
The project is released under the MIT License. Consult `LICENSE` file for more details.
## Acknowledgments π
- Hats off to `spaCy` and `TextBlob` artisans, trailblazers in the NLP domain.
- Salute to the Python community's collaborative ethos, a wellspring of inspiration and innovation.