README.md

metadata

title: Bertimbau Finetuned Glassdoor Reviews
emoji: 🏢
colorFrom: gray
colorTo: green
sdk: streamlit
sdk_version: 1.41.1
app_file: app.py
pinned: false
license: mit
short_description: Sentiment Analysis of Glassdoor reviews using BERTimbau

Bertimbau Finetuned Glassdoor Reviews

This project provides a Streamlit web application for classifying Glassdoor reviews into sentiment categories using a fine-tuned BERT model. The model is based on the pre-trained BERT model from neuralmind/bert-base-portuguese-cased and fine-tuned on Glassdoor review data.

Model

The model architecture and training process can be found at glassdoor-reviews-analysis-nlp.

Installation

To run this project locally, follow these steps:

1. Download the pytorch_model.bin from stevillis/bertimbau-finetuned-glassdoor-reviews.

2. Clone the repository:

   git clone https://github.com/your-username/bertimbau-finetuned-glassdoor-reviews.git
   cd bertimbau-finetuned-glassdoor-reviews
   

3. Create a virtual environment and activate it:

   python -m venv venv
   source venv/bin/activate  # On Windows, use `venv\Scripts\activate`
   

4. Install the required dependencies:

   pip install -r requirements.txt
   

5. Move the pytorch_model.bin to bertimbau-finetuned-glassdoor-reviews directory.

6. Run the Streamlit application:

   streamlit run app.py
   

Usage

1. Open your web browser and go to http://localhost:8501.
2. Enter a Glassdoor review text in the input box.
3. The application will display the predicted sentiment and its corresponding score.