This is a fine-tuned bert-based-uncased model trained to classify news. It was trained on this BBC news dataset. Below is the citation for said dataset:
Greene, D., & Cunningham, P. (2006). Practical Solutions to the Problem of Diagonal Dominance in Kernel Document Clustering. Proc. 23rd International Conference on Machine Learning (ICML’06), 377–384.
https://doi.org/10.1145/1143844.1143892This is just one of three models I trained for my project, but was the only one I uploaded as it is being deployed on Streamlit. You can find the link to that here:
https://oq4zyh8wx5jpwaky4bkqbl.streamlit.app/Additionally, here's the link to the GitHub repository for my project. This includes a written report of the data. It was quite fascinating!
https://github.com/SirCacto/MachineLearningNLPProject
