README.md

---
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](https://huggingface.co/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](https://github.com/stevillis/glassdoor-reviews-analysis-nlp).

## Installation

To run this project locally, follow these steps:

1. Download the [pytorch_model.bin](https://huggingface.co/stevillis/bertimbau-finetuned-glassdoor-reviews/blob/main/pytorch_model.bin) from `stevillis/bertimbau-finetuned-glassdoor-reviews`.

2. Clone the repository:
    ```sh
    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:
    ```sh
    python -m venv venv
    source venv/bin/activate  # On Windows, use `venv\Scripts\activate`
    ```

4. Install the required dependencies:
    ```sh
    pip install -r requirements.txt
    ```

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

6. Run the Streamlit application:
    ```sh
    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.