https://github.com/crypto-artisan/review-analysis
Sentiment Analysis for customer Reviews
https://github.com/crypto-artisan/review-analysis
Last synced: 2 months ago
JSON representation
Sentiment Analysis for customer Reviews
- Host: GitHub
- URL: https://github.com/crypto-artisan/review-analysis
- Owner: crypto-artisan
- Created: 2024-02-19T09:53:58.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-02-19T09:54:12.000Z (over 1 year ago)
- Last Synced: 2025-01-19T22:22:49.190Z (4 months ago)
- Language: Python
- Size: 30.3 KB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Review Scraper
Website that scrapes Google for reviews of an item (product, movie, etc.) and runs sentiment analysis on result descriptions
LIVE at [reviewscrper.streamlit.app](https://reviewscrper.streamlit.app/)!
TIP: Be specific e.g. `PS5 console` not `PS5`
## What it uses
- *Huggingface* for sentiment analysis
- Uses `LiYuan/amazon-review-sentiment-analysis` for 1-5 star rating
- Uses `cardiffnlp/twitter-roberta-base-sentiment-latest` for positive/neutral/negative sentiment
- *Apify* for scraping Google
- *Streamlit* for hosting the website
- *WordCloud* for word clouds
## Demo
## How to host locally
1. Install requirements
```
pip install -r requirements.txt
```
3. Make an account on [Apify](https://apify.com/)
4. Create the file `/.streamlit/secrets.toml` with the contents:
```
APIFY_TOKEN='YOUR_API_TOKEN'
```
2. Run `main.py`
```
streamlit run main.py
```
## References
- Inspired by [nus-sentiment](https://github.com/nus-sentiment/nus-sentiment)