NLP-Huggingface-Covid-19-Tweet-Sentiment-Analysis

In this project, we will be fine-tuning text classification NLP models from huggingface with Covid-19 tweet data to build a model that classifies text based on Covid-19 vaccine sentiment.We will fine tune the RoBERTa model to categorize sentiments expressed in a vast collection of COVID-19-related tweets. We will then build a Gradio app for our model to give our model an interface and host it on huggingface

Project Links 📑

• Tweet Sentiment Analysis Roberta: Model Fine Tuning process.
• main.py: Gradio app
• Data: Training and testing datasets for model development.
• Hugging Face Space: Gradio app deployed on Huggingface

Getting Started🏁

You need to have Python 3 on your system. Then you can clone this repo and being at the repo's root :: repository_name> ...

1. Clone this repository: git clone https://github.com/Azie88 NLP-Huggingface-Covid-19-Tweet-Sentiment-Analysis
2. On your IDE, create A Virtual Environment and Install the required packages for the project:

• Windows:

    python -m venv venv; 
    venv\Scripts\activate; 
    python -m pip install -q --upgrade pip; 
    python -m pip install -qr requirements.txt  
  

• Linux & MacOs:

    python3 -m venv venv; 
    source venv/bin/activate; 
    python -m pip install -q --upgrade pip; 
    python -m pip install -qr requirements.txt  
  

The two long command-lines have the same structure. They pipe multiple commands using the symbol ; but you can manually execute them one after the other.

• Create the Python's virtual environment that isolates the required libraries of the project to avoid conflicts;
• Activate the Python's virtual environment so that the Python kernel & libraries will be those of the isolated environment;
• Upgrade Pip, the installed libraries/packages manager to have the up-to-date version that will work correctly;
• Install the required libraries/packages listed in the requirements.txt file so that they can be imported into the python script and notebook without any issue.

NB: For MacOs users, please install Xcode if you have an issue.

3. Run the Gradio app (being at the repository root):

Gradio:

For development

  gradio main.py

For normal deployment/execution

  python main.py  

• Go to your browser at the following address :

  http://localhost:7860

4. Run the jupyter notebook on colab for more indepth insights on the deep learning process.

App Screenshots 🖼️

Gradio App on Huggingface

Author✍️

Andrew Obando

---

Feel free to star ⭐ this repository if you find it helpful!