Sentiment Classification of Thai NBA Comments Using WangchanBERTa-Finetuned

Introduction

This project uses the WangchanBERTa transformer model to classify Thai NBA comments into Positive, Neutral, and Negative sentiments. It leverages a dataset of 500 comments sourced from a Facebook fanpage. The model is trained and evaluated using Hugging Face’s tools to provide insights into fan sentiment

Dataset

The dataset consists of 500 Thai comments about the NBA from a Facebook fanpage. The data is stored in an Excel file with the following columns:

• text: The comment text.

• label: The sentiment label, which can be 'POS', 'Neu', or 'Neg'.

Results

• Accuracy: 72.00 %

• Precision: 76.00 %

• Recall: 72.00 %

• F1 Score: 72.75 %

Contributing

Contributions are welcome! Please fork this repository and submit pull requests for any improvements or bug fixes.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

• Hugging Face for providing the transformers library.

• Poom-sci for the WangchanBERTa-finetuned-sentiment model.